© 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. 53459
    Prev
    Next
    INDEX
    Explanations

    comparing to others or previous

    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
    å¼ģ
    -0.10
    ä¸įå®ľ
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    ãģĹãģĭ
    -0.09
    è´«ç©·
    -0.09
     only
    -0.08
    æľĢå¤ļ
    -0.08
    8
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    æĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
     полно
    0.12
    èĩªå¦Ĥ
    0.11
    è½°
    0.10
    éĺ¶
    0.10
     peÅĤne
    0.10
    éĤ£ç§į
    0.10
    éĤ£æ¬¡
    0.10
    è¾īçħĮ
    0.10
    åºij
    0.09
    æŁIJäºĽ
    0.09
    Activations Density 0.084%

    No Known Activations