© 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. 111759
    Prev
    Next
    INDEX
    Explanations

    hygiene or hy-prefix names/places

    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
    uchar
    -0.10
    olini
    -0.10
    urable
    -0.10
    thew
    -0.10
    kest
    -0.10
    /User
    -0.09
    ctic
    -0.09
     trouble
    -0.09
    ORS
    -0.09
    hattan
    -0.09
    POSITIVE LOGITS
    bla
    0.12
    phen
    0.11
    afil
    0.10
    acin
    0.09
    att
    0.09
     attendant
    0.09
    amt
    0.08
    ades
    0.08
    dg
    0.08
    Josh
    0.08
    Activations Density 0.042%

    No Known Activations