© 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. 111526
    Prev
    Next
    INDEX
    Explanations

    " for "

    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
     everyone
    -0.10
     people
    -0.10
     users
    -0.10
     erv
    -0.09
     anyone
    -0.09
    Anyone
    -0.09
    icity
    -0.09
     citizens
    -0.09
     consumers
    -0.09
     players
    -0.09
    POSITIVE LOGITS
     whose
    0.12
    whose
    0.12
    their
    0.10
    /th
    0.10
     their
    0.10
     theirs
    0.10
     it
    0.10
     Vita
    0.10
     Sundays
    0.09
    who
    0.09
    Activations Density 0.136%

    No Known Activations