© 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. 52693
    Prev
    Next
    INDEX
    Explanations

    appeal, file, serve, quit, marry

    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
    纵横
    -0.11
    è£ģ
    -0.10
    _Float
    -0.10
    æ»ļ
    -0.10
    éĤ£æł·
    -0.10
    åŁİéķĩ
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
     recl
    -0.09
    主宰
    -0.09
    çĭŀ
    -0.09
    POSITIVE LOGITS
    çļĦæĢģ度
    0.09
    ë²Ī
    0.08
    çļĦå¿ĥæĢģ
    0.08
    çļĦçľ¼ç¥ŀ
    0.08
    çIJ´
    0.08
    æĢģ度
    0.08
    çļĦå¿ĥ
    0.08
    æĽ´å¤ļ
    0.08
    ä¾
    0.07
    èĻ
    0.07
    Activations Density 0.211%

    No Known Activations