© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    internal self

    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
    {:
    -0.09
     themselves
    -0.08
    é¦ĸåıij
    -0.08
    è¿ĽæŃ¥
    -0.08
     gaze
    -0.08
    éĢĤåIJĪèĩªå·±
    -0.08
    éļ¾
    -0.08
    çļĦè¿ĽæŃ¥
    -0.08
     Gust
    -0.07
     nu
    -0.07
    POSITIVE LOGITS
    åijĬè¯ī她
    0.11
     говоÑĢиÑĤ
    0.11
    说æľį
    0.11
    åijĬ訴
    0.10
    æĹ©æĹ©
    0.10
     ÑģообÑīаеÑĤ
    0.10
    è´ª
    0.09
     Tells
    0.09
    ç«Ļèµ·æĿ¥
    0.09
    çĿ¬
    0.09
    Activations Density 0.028%

    No Known Activations