© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 57395
    Prev
    Next
    INDEX
    Explanations

    both"},# "supervision" in MAX_ACTIVATING_TOKENS and "Both" in TOP_ACTIVATING_TEXTS suggest identifying instances where "both" is used as a conjunction or to indicate a pair.# Other words like "patients", "ideas", "sandals" also appear.# The most consistent pattern is the usage of "both" in phrases like "both ... and ...", "both as ... or ...", "both ... and ...", "both ... and ...", "both ... and ...", "both ... and ...", "both ... and ...", "both ... and ...", "both ... and ...", "both ... and ...".# Therefore, the neuron is likely detecting the usage of "both".the neuron detects the word "both"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    era
    -0.11
     respectively
    -0.11
    EDI
    -0.11
    缸
    -0.10
    chan
    -0.10
    ernes
    -0.10
     etc
    -0.10
    ffer
    -0.10
    EAR
    -0.10
    FER
    -0.09
    POSITIVE LOGITS
    ãĤ¹ãĥĪ
    0.08
     Meg
    0.07
     sides
    0.07
    avan
    0.07
    amera
    0.07
     fals
    0.07
     meg
    0.07
     barrel
    0.07
     pent
    0.07
    weg
    0.06
    Activations Density 0.108%

    No Known Activations