© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90571
    Prev
    Next
    INDEX
    Explanations

    outrage / horrified / shocked

    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
    icha
    -0.11
     omin
    -0.11
     Tage
    -0.10
     eerie
    -0.10
    [min
    -0.10
     dispose
    -0.10
    abi
    -0.10
     sut
    -0.09
     stub
    -0.09
    /utility
    -0.09
    POSITIVE LOGITS
     horrified
    0.12
     shocked
    0.12
     scandal
    0.12
     indign
    0.12
     horror
    0.11
    ingly
    0.11
    /am
    0.10
     shock
    0.10
     SOS
    0.10
     shri
    0.10
    Activations Density 0.023%

    No Known Activations