© 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. 10321
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
    交代
    -0.09
    çīĴ
    -0.09
    åIJĦ个çݯèĬĤ
    -0.09
    çŁŃçŁŃ
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    çĤ½
    -0.09
    æĸ¹éĿ¢
    -0.09
    èµ·åĪĿ
    -0.09
    ä¸ĭä¸ĢæŃ¥
    -0.08
    éĺŁéķ¿
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻ
    0.09
    åľ¨ä»ĸçļĦ
    0.09
    ILLE
    0.09
    ç»Łè®¡æķ°æį®
    0.09
     Dig
    0.09
    æĮĩåĩº
    0.09
    è¯ļä¿¡
    0.08
    iglia
    0.08
    ä»ĸçļĦ
    0.08
    ä¸İæѤ
    0.08
    Activations Density 0.148%

    No Known Activations