© 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. 49514
    Prev
    Next
    INDEX
    Explanations

    attack, bite, killed, or venomous encounter

    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
     gag
    -0.09
     liquid
    -0.08
     abuse
    -0.08
    Disposed
    -0.08
     figur
    -0.08
     oy
    -0.08
     vinc
    -0.08
     language
    -0.08
     fung
    -0.08
     electronically
    -0.08
    POSITIVE LOGITS
     bitten
    0.31
     bite
    0.28
     bites
    0.26
     Bite
    0.25
    bite
    0.25
     mau
    0.20
     attacked
    0.20
     attack
    0.18
     Attack
    0.18
     ATTACK
    0.18
    Activations Density 0.571%

    No Known Activations