© 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. 63802
    Prev
    Next
    INDEX
    Explanations

    great scale or amount

    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
    æĹłä¸į
    -0.10
    ä¸į失
    -0.10
    çĤ¹æ»´
    -0.10
    è¶³å¤ŁçļĦ
    -0.09
    æĽ´å¤ļ
    -0.09
    ãģĵãģĿ
    -0.08
    æĽ´å¥½çļĦ
    -0.08
    rather
    -0.08
     eher
    -0.08
    æĽ´å¥½åľ°
    -0.08
    POSITIVE LOGITS
    æĬķåħ¥åĪ°
    0.11
    æīĶ
    0.09
    æ¶Įåħ¥
    0.09
    èĩªåĬ¨åĮĸ
    0.09
    è¿Ļ个ä¸ĸçķĮ
    0.09
    èĦijåŃIJéĩĮ
    0.09
    å°±åľ¨äºİ
    0.09
    alley
    0.09
    è¿Ļå¥Ĺ
    0.09
    é³ĸ
    0.09
    Activations Density 0.163%

    No Known Activations