© 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. 18736
    Prev
    Next
    INDEX
    Explanations

    violence and criminal acts

    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
     whatever
    -0.12
     or
    -0.10
     whatsoever
    -0.10
    whatever
    -0.10
     anything
    -0.10
     Whatever
    -0.08
    Whatever
    -0.08
    ...
    -0.08
    izen
    -0.08
     oder
    -0.08
    POSITIVE LOGITS
     Instances
    0.11
     INCLUDING
    0.10
    Âł↵
    0.10
     unspecified
    0.10
    Fade
    0.10
     Accord
    0.10
    Instances
    0.10
     Helm
    0.10
     twice
    0.10
    sol
    0.10
    Activations Density 0.015%

    No Known Activations