© 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. 60928
    Prev
    Next
    INDEX
    Explanations

    still pursuing

    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
    çİ°åľ¨å·²ç»ı
    -0.10
    ÑĪиб
    -0.10
    åĨį次
    -0.09
    nip
    -0.09
    hap
    -0.09
     Zap
    -0.09
    ÑĢÑĥб
    -0.09
    elyn
    -0.09
    ä¸įä½Ĩ
    -0.09
     дейÑģÑĤвиÑĤелÑĮно
    -0.08
    POSITIVE LOGITS
    born
    0.11
    ä¿ĿæĮģçĿĢ
    0.10
    /new
    0.10
    åģľçķĻåľ¨
    0.10
    birth
    0.10
    åıijå±ķéĺ¶æ®µ
    0.10
    éĿ¢çĽ®
    0.09
    å±ĢéĻIJäºİ
    0.09
    åŃĺåľ¨çļĦ
    0.09
    åŃĺåľ¨
    0.09
    Activations Density 0.038%

    No Known Activations