© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23769
    Prev
    Next
    INDEX
    Explanations

    performing technical tasks

    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
    ero
    -0.10
    ä¸įèĥ½ä¸ºç©º
    -0.09
    æĬĢæľ¯åĴĮ
    -0.09
     hand
    -0.09
    æĴŃåĩº
    -0.08
    é»ij马
    -0.08
    wk
    -0.08
    æ´Ĺ澡
    -0.08
    æĬĢæľ¯æ°´å¹³
    -0.08
    ansa
    -0.08
    POSITIVE LOGITS
    åĩĨç¡®
    0.09
     Downs
    0.09
    è¿ħéĢŁ
    0.09
    大éĿ¢ç§¯
    0.08
    顽
    0.08
    iris
    0.08
    精确
    0.08
    å¿«éĢŁ
    0.08
    èį¯æĿIJ
    0.08
    顺åĪ©
    0.08
    Activations Density 0.339%

    No Known Activations