© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11646
    Prev
    Next
    INDEX
    Explanations

    finding continued enjoyment

    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
    éĨĴäºĨ
    -0.09
    åı¯ä»¥è¯´
    -0.09
    庶
    -0.09
    é¹ľ
    -0.09
    åı¯ä»¥è¯´æĺ¯
    -0.09
    aping
    -0.08
    æ±
    -0.08
    æľīä¸Ģå®ļ
    -0.08
    æķĻä½ł
    -0.08
    大å®Ĺ
    -0.08
    POSITIVE LOGITS
    æ²Ļé¾Ļ
    0.12
     ìķŀìľ¼ë¡ľ
    0.11
    åľ¨æľªæĿ¥
    0.11
    好人
    0.10
    祺
    0.10
    ç»§ç»Ńä¿ĿæĮģ
    0.10
    жд
    0.10
    çļĦç¾İ好
    0.10
    顺åĪ©
    0.10
    é¼ł
    0.10
    Activations Density 0.026%

    No Known Activations