© 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. 15889
    Prev
    Next
    INDEX
    Explanations

    assaults, raids, invasions, harassment, stalking

    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
    uye
    -0.10
     fy
    -0.10
    urve
    -0.10
    eel
    -0.10
    <<<
    -0.09
     rele
    -0.09
    icky
    -0.09
    serv
    -0.09
     Fraud
    -0.09
     Colbert
    -0.09
    POSITIVE LOGITS
    /host
    0.12
    ëĭ¹
    0.12
    -su
    0.11
    /dom
    0.10
     violently
    0.10
    /exp
    0.09
    ers
    0.09
    /man
    0.09
    -force
    0.09
     force
    0.09
    Activations Density 0.110%

    No Known Activations