© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113680
    Prev
    Next
    INDEX
    Explanations

    regardless of whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipt
    -0.12
     Fine
    -0.12
    lec
    -0.11
    _gallery
    -0.11
    anst
    -0.11
    ror
    -0.11
    pear
    -0.11
    --[
    -0.11
    -gray
    -0.11
     Incorporated
    -0.11
    POSITIVE LOGITS
     obviously
    0.07
     whether
    0.07
    /un
    0.07
    atham
    0.07
     of
    0.07
     depress
    0.06
     obvious
    0.06
     Bened
    0.06
    ernet
    0.06
    iving
    0.06
    Activations Density 0.003%

    No Known Activations