© 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. 28499
    Prev
    Next
    INDEX
    Explanations

    licence keys and activation codes

    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
     punishments
    -0.11
    pun
    -0.11
     auxiliary
    -0.10
    reb
    -0.10
     punishment
    -0.10
     McL
    -0.09
     accompanying
    -0.09
    alic
    -0.09
     Monk
    -0.09
    uby
    -0.09
    POSITIVE LOGITS
     STILL
    0.12
     plagiar
    0.11
    ç«
    0.11
     someone
    0.11
     disob
    0.11
     somebody
    0.11
     moo
    0.10
     lipstick
    0.10
     slog
    0.10
     fid
    0.10
    Activations Density 0.007%

    No Known Activations