© 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. 58036
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier

    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
     flood
    -0.07
    cour
    -0.06
     nod
    -0.06
     Leer
    -0.06
     dist
    -0.06
     c
    -0.06
     read
    -0.06
    nod
    -0.06
     cord
    -0.06
     bankruptcy
    -0.06
    POSITIVE LOGITS
    -License
    0.21
     Consolid
    0.12
    izedName
    0.11
     Imaging
    0.11
    spawn
    0.10
    unning
    0.10
    wolf
    0.10
    YS
    0.10
    pricing
    0.10
    ured
    0.10
    Activations Density 0.001%

    No Known Activations