© 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. 63847
    Prev
    Next
    INDEX
    Explanations

    use or used

    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
    Negative Logits
    ught
    -0.09
    æ¿ĢåĬ¨
    -0.08
    ç§ijæķĻ
    -0.08
    icus
    -0.08
    ä¼ŀ
    -0.08
    bish
    -0.08
    å¿ĸ
    -0.08
    ÑģÑĤвенно
    -0.07
    reich
    -0.07
    æ±Ĭ
    -0.07
    POSITIVE LOGITS
    åıĺå¾Ĺ
    0.17
    ä¸įåĨį
    0.17
    åıĺå¾ĹæĽ´
    0.16
    ä»İæѤ
    0.16
    åĨįä¹Łä¸į
    0.15
    èĩªæѤ
    0.15
    è¶ĬæĿ¥è¶Ĭ
    0.15
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    0.15
    åıĺå¾ĹæĽ´åĬł
    0.15
     become
    0.15
    Activations Density 0.763%

    No Known Activations