© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7824
    Prev
    Next
    INDEX
    Explanations

    latest developments

    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
    ç©¿æ¢Ń
    -0.10
    uet
    -0.09
    å¾Ĺä½ı
    -0.08
    BALL
    -0.08
    åį°èĬ±
    -0.08
    ball
    -0.08
    ç¨ļ
    -0.08
    æĪIJæŀľè½¬åĮĸ
    -0.08
    _DEPRECATED
    -0.08
    fight
    -0.08
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.12
    ressed
    0.10
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
    วà¸ĩ
    0.09
    ç»´å¥ĩ
    0.09
    äºİæѤ
    0.09
    äºĭå®ľ
    0.09
    åĨįæĿ¥
    0.09
    ekte
    0.09
    ements
    0.08
    Activations Density 0.011%

    No Known Activations