© 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. 26407
    Prev
    Next
    INDEX
    Explanations

    wondering why or how

    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
    æģ©
    -0.10
    éĿŀ常éĩįè¦ģ
    -0.10
    è¿Ļåĩłä¸ª
    -0.09
    æ·±çŁ¥
    -0.09
    .tb
    -0.09
    éļıåį³
    -0.08
    éĿŀ常æĺİæĺ¾
    -0.08
    jee
    -0.08
    åºľ
    -0.08
    èİ·å¾ĹäºĨ
    -0.08
    POSITIVE LOGITS
    æĺ¯åIJ¦åŃĺåľ¨
    0.12
    æĥ³è¿ĩ
    0.10
    çĦ¶æĺ¯
    0.10
    éªħ
    0.09
    _NATIVE
    0.09
     wonders
    0.09
    æĺ¯åIJ¦æľī
    0.09
    é¢Ħè§ģ
    0.09
    ä¸ĢåĪĨéĴŁ
    0.09
    æķĪ
    0.08
    Activations Density 0.018%

    No Known Activations