© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40055
    Prev
    Next
    INDEX
    Explanations

    big deal or no big deal

    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
    è¡ĮæĶ¿æľºåħ³
    -0.09
    (&(
    -0.09
    è¿Ļä¸Ģå¹´
    -0.09
    æĿĤçī©
    -0.09
    该éĻ¢
    -0.09
    æļĤ
    -0.09
    nesc
    -0.09
     Daniels
    -0.09
    ChangeListener
    -0.08
    人å±ħçݯå¢ĥ
    -0.08
    POSITIVE LOGITS
    åIJİæŀľ
    0.10
    æĺ¯ä¸Ģ件
    0.09
    itized
    0.08
    edio
    0.08
     crop
    0.08
    aki
    0.08
    าะ
    0.08
    åĢ¼å¾Ĺåħ³æ³¨
    0.08
    è¾ľ
    0.08
    èĬĿ麻
    0.08
    Activations Density 0.041%

    No Known Activations