© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49260
    Prev
    Next
    INDEX
    Explanations

    combat, battle, fight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    è´¢åĬĽ
    -0.10
    迤
    -0.10
    éĴ±åĮħ
    -0.10
    èĭķ
    -0.09
    çİĭåĽ½
    -0.09
    è¿Ľä¸ĢæŃ¥
    -0.09
    使åĬ²
    -0.09
    èĶ«
    -0.09
    estic
    -0.09
    GENER
    -0.09
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.09
    æĢ»çĽij
    0.08
    鬥
    0.08
    æ¿ĢçĥĪçļĦ
    0.08
    èµŀ
    0.08
    ëĭ´
    0.08
    .DataContext
    0.08
    æĸĹ
    0.08
    讲究
    0.08
     Fare
    0.08
    Activations Density 0.034%

    No Known Activations