© 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. 10736
    Prev
    Next
    INDEX
    Explanations

    willingness to do something

    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
    /cop
    -0.10
    主è¦ģåĨħ容
    -0.10
    èĪ¬
    -0.09
    éģı
    -0.09
    è®°å¾Ĺ
    -0.09
    åIJİåĨį
    -0.09
    æľĭåıĭåľĪ
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    好è¿IJ
    -0.09
    è¿ĺè®°å¾Ĺ
    -0.09
    POSITIVE LOGITS
    çīºçī²
    0.10
    éĵ¤
    0.10
    ych
    0.10
    æī¿æĭħ责任
    0.09
    orsi
    0.09
    CDATA
    0.09
     sacrificing
    0.08
    ç¿¥
    0.08
     Sacr
    0.08
    anguard
    0.08
    Activations Density 0.009%

    No Known Activations