© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    verbs describing states or actions

    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
    «
    -0.11
     Campo
    -0.10
    âĢ¦
    -0.10
     preventative
    -0.10
     —
    -0.09
     practically
    -0.09
    unte
    -0.09
    -an
    -0.09
     hence
    -0.09
     hopefully
    -0.09
    POSITIVE LOGITS
     Saying
    0.11
    ENU
    0.10
     disliked
    0.10
     saying
    0.10
     confl
    0.09
     '),
    0.09
     Eugene
    0.09
     miscellaneous
    0.09
     Lew
    0.09
     such
    0.09
    Activations Density 1.195%

    No Known Activations