© 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. 22322
    Prev
    Next
    INDEX
    Explanations

    and seamless, and a, and Knight, and inserted

    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
    æĥŁ
    -0.10
    çļĦ产åĵģ
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
    讲æķħäºĭ
    -0.09
    å«Į
    -0.09
    第ä¸ĢæŃ¥
    -0.09
    å¢Ļä¸Ĭ
    -0.09
    ç»ĦåĽ¢
    -0.08
    éĿ¢ç§¯çº¦
    -0.08
    æİĴåIJį第
    -0.08
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.09
    à°¬
    0.09
    /jav
    0.09
    -INF
    0.09
    akens
    0.09
    æŁIJäºĽ
    0.08
    åŁºç¡Ģ
    0.08
    缸åºĶ
    0.08
    çĤ¯
    0.08
    .showMessageDialog
    0.08
    Activations Density 0.475%

    No Known Activations