© 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. 90107
    Prev
    Next
    INDEX
    Explanations

    physical assault or attack

    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
     langs
    -0.13
     lurking
    -0.12
     dall
    -0.12
     lure
    -0.11
    fov
    -0.11
     vibrating
    -0.11
     intrig
    -0.11
     siden
    -0.11
     abrupt
    -0.11
     standoff
    -0.11
    POSITIVE LOGITS
     punches
    0.30
     punching
    0.26
     repeatedly
    0.23
     punch
    0.19
     Punch
    0.19
     fists
    0.19
     barrage
    0.19
     attacks
    0.18
     attack
    0.18
     beating
    0.18
    Activations Density 0.093%

    No Known Activations