© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17163
    Prev
    Next
    INDEX
    Explanations

    violent actions and events

    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
    ritte
    -0.10
    ItemImage
    -0.10
     kole
    -0.10
     Serv
    -0.10
     ongoing
    -0.10
    UrlParser
    -0.10
     Hint
    -0.10
    <{
    -0.10
    ViewItem
    -0.10
     Carnegie
    -0.10
    POSITIVE LOGITS
     itself
    0.21
     proper
    0.12
    proper
    0.10
     proposal
    0.09
     which
    0.09
     commence
    0.08
    aci
    0.08
    (s
    0.08
     Proper
    0.08
     date
    0.07
    Activations Density 0.460%

    No Known Activations