© 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. 25139
    Prev
    Next
    INDEX
    Explanations

    assigned responsibility or to

    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
     Assignment
    -0.14
     assignment
    -0.14
     assignments
    -0.13
    assignment
    -0.11
    assignments
    -0.11
    Assignment
    -0.10
    instructions
    -0.10
     ASSIGN
    -0.09
     Assign
    -0.09
    _assignment
    -0.08
    POSITIVE LOGITS
     to
    0.11
     shorten
    0.10
     guilt
    0.09
    eed
    0.09
     tilt
    0.09
     tails
    0.09
     case
    0.09
    toList
    0.09
    ned
    0.09
     Hover
    0.09
    Activations Density 0.016%

    No Known Activations