© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14029
    Prev
    Next
    INDEX
    Explanations

    pencil related words

    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
    Negative Logits
    van
    -0.11
     lor
    -0.11
    Unnamed
    -0.10
     Lor
    -0.10
    lor
    -0.09
    ude
    -0.09
     Platt
    -0.09
    (ver
    -0.09
     Sung
    -0.09
     bist
    -0.09
    POSITIVE LOGITS
     DEM
    0.09
    roi
    0.08
    peater
    0.08
    blur
    0.08
     whoever
    0.08
     cut
    0.08
    274
    0.08
     loophole
    0.08
     overlooking
    0.08
    mana
    0.08
    Activations Density 0.001%

    No Known Activations