© 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. 5962
    Prev
    Next
    INDEX
    Explanations

    head coach

    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
    ech
    -0.09
    éĤ£æ¬¡
    -0.09
    ningen
    -0.09
    ooter
    -0.09
    çIJĨäºĭéķ¿
    -0.09
    ä¸ĢåıĮ
    -0.08
    _VERBOSE
    -0.08
    esy
    -0.08
    æĺ¥èĬĤæľŁéĹ´
    -0.08
    å±Ĥ次
    -0.08
    POSITIVE LOGITS
    å¼Ń
    0.08
    æķĻåŃ¦è´¨éĩı
    0.08
    åĮĸåIJĪ
    0.08
    ÑĦа
    0.08
    人éĹ´
    0.08
    人èĦ¸
    0.08
    æĦ«
    0.08
    åł´åIJĪ
    0.08
    ä»¥äººä¸ºæľ¬
    0.08
    磶
    0.08
    Activations Density 0.057%

    No Known Activations