© 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. 49363
    Prev
    Next
    INDEX
    Explanations

    killings and shootings

    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
     thieves
    -0.12
     disappearing
    -0.10
     prisoner
    -0.10
     disappearance
    -0.10
     Dangerous
    -0.10
    Spy
    -0.10
     imprison
    -0.10
    /Search
    -0.10
     imprisonment
    -0.10
     inadvert
    -0.09
    POSITIVE LOGITS
     massacre
    0.21
     rampage
    0.20
     massac
    0.17
     indiscrim
    0.17
     shootings
    0.17
     motive
    0.17
     sla
    0.16
     slaughter
    0.15
     gunman
    0.15
     motives
    0.14
    Activations Density 0.575%

    No Known Activations