© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    killer instinct, whales, spy, video

    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
    ses
    -0.10
    lec
    -0.09
    le
    -0.08
    eba
    -0.08
     sque
    -0.08
    ing
    -0.08
     celebration
    -0.08
    eer
    -0.08
    sy
    -0.08
    iba
    -0.08
    POSITIVE LOGITS
     instinct
    0.19
     instincts
    0.17
     whale
    0.15
     Inst
    0.15
     killer
    0.14
     whales
    0.14
     Killer
    0.12
    Inst
    0.11
    -inst
    0.11
    killer
    0.11
    Activations Density 0.009%

    No Known Activations