© 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. 21754
    Prev
    Next
    INDEX
    Explanations

    hesitant, shy, reluctant

    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
    æģ£
    -0.10
    åĴĮåıijå±ķ
    -0.09
    zik
    -0.09
    ä¸İåıijå±ķ
    -0.09
    çĥ¤
    -0.09
    åľ¨æł¡
    -0.08
    pike
    -0.08
    èµŀ
    -0.08
    好è¿IJ
    -0.08
    åıijå±ķåīįæĻ¯
    -0.08
    POSITIVE LOGITS
     ngại
    0.17
    ä¸įæĦ¿æĦı
    0.15
    ä¸įæĦ¿
    0.14
    ä¸į好æĦıæĢĿ
    0.14
    èĪįä¸įå¾Ĺ
    0.13
    害ç¾ŀ
    0.13
    å¿Į
    0.13
    ä¸įæķ¢
    0.13
     reluctance
    0.13
    害æĢķ
    0.12
    Activations Density 0.056%

    No Known Activations