© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5165
    Prev
    Next
    INDEX
    Explanations

    driver or driver-related terms

    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
    eker
    -0.11
    sla
    -0.11
     Presidents
    -0.10
    eming
    -0.10
     Verm
    -0.10
    orte
    -0.10
    piel
    -0.09
     coordin
    -0.09
    PY
    -0.09
    ibel
    -0.09
    POSITIVE LOGITS
    less
    0.14
    /pass
    0.11
    oose
    0.09
     unions
    0.09
    .quit
    0.09
    noon
    0.09
    /users
    0.09
     hon
    0.09
    ing
    0.08
    union
    0.08
    Activations Density 0.043%

    No Known Activations