© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21872
    Prev
    Next
    INDEX
    Explanations

    willingness to act

    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
    ãģ¤ãģĦ
    -0.10
    خت
    -0.09
    æ´İ
    -0.09
     ÑģÑĤÑĢем
    -0.09
    ç»ĻäºĨæĪij
    -0.09
    rosis
    -0.09
    å¿ħé¡»è¦ģ
    -0.09
    è¦ģåİ»
    -0.09
    總æĺ¯
    -0.09
    符
    -0.09
    POSITIVE LOGITS
    æīįè¡Į
    0.10
    åĵªæĢķæĺ¯
    0.10
    éĴ°
    0.09
    åĵªæĢķ
    0.09
     ENC
    0.08
    å¸®ä½ł
    0.08
    ä¸ĸ家
    0.08
    æī¿æĭħ
    0.08
    uala
    0.08
    åŃº
    0.08
    Activations Density 0.034%

    No Known Activations