© 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. 47742
    Prev
    Next
    INDEX
    Explanations

    among

    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
    é£İ鼨
    -0.08
    oriously
    -0.08
    หมà¸Ķ
    -0.08
     Trap
    -0.08
    两次
    -0.08
    ArrayOf
    -0.08
    ListOf
    -0.08
    ares
    -0.08
    uits
    -0.07
    æł¼å°Ķ
    -0.07
    POSITIVE LOGITS
    æİĤ
    0.10
    çļĦæĹ¥åŃIJ
    0.09
    éĩįè¦ģåĽłç´ł
    0.09
    çĸ¼
    0.09
    å´´
    0.09
    磶
    0.09
    دÙĪا
    0.09
    æħij
    0.09
    éĢ¶
    0.08
    JOR
    0.08
    Activations Density 0.068%

    No Known Activations