© 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. 47128
    Prev
    Next
    INDEX
    Explanations

    attack or fight stance

    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
    avig
    -0.10
    756
    -0.09
     Extr
    -0.09
     kiss
    -0.08
     triumph
    -0.08
    olis
    -0.08
    pen
    -0.08
     award
    -0.08
    amage
    -0.08
     rewarded
    -0.08
    POSITIVE LOGITS
     attacked
    0.18
     readiness
    0.18
     Ready
    0.17
     ATTACK
    0.17
     ready
    0.17
     attack
    0.17
     charging
    0.17
     challenge
    0.17
     challenger
    0.16
     fight
    0.16
    Activations Density 0.135%

    No Known Activations