© 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. 47777
    Prev
    Next
    INDEX
    Explanations

    calculate or programming logic

    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
    <|fim_middle|>
    -0.08
    skins
    -0.08
     _______,
    -0.08
     accessor
    -0.08
     Pornhub
    -0.07
    alars
    -0.07
     Porno
    -0.07
     porno
    -0.07
     xnxx
    -0.07
     fasc
    -0.07
    POSITIVE LOGITS
     vs
    0.11
     Pert
    0.11
    ahn
    0.10
     Vern
    0.10
     forced
    0.10
     quar
    0.10
    .gateway
    0.10
     Forced
    0.10
    andard
    0.10
    Guy
    0.09
    Activations Density 0.008%

    No Known Activations