© 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
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3372
    Prev
    Next
    INDEX
    Explanations

    beginning of the phrase "although"

    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
    ;++
    -0.09
    elman
    -0.09
    quet
    -0.09
    ä»
    -0.09
     concurrently
    -0.08
    ome
    -0.07
    ups
    -0.07
    er
    -0.07
     Roll
    -0.07
    Flying
    -0.07
    POSITIVE LOGITS
     oltre
    0.10
    ático
    0.09
    too
    0.09
    /pg
    0.09
    rawl
    0.09
    eature
    0.09
    rov
    0.09
    eatures
    0.09
    Offsets
    0.09
    cdc
    0.09
    Activations Density 0.045%

    No Known Activations