© 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. 35976
    Prev
    Next
    INDEX
    Explanations

    new and confirmed leaks

    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
    ç¹ģ
    -0.09
    ä»ĺ
    -0.09
    绣çŃ¹
    -0.09
    å°Ĩèĩªå·±çļĦ
    -0.09
     маÑĢÑĪ
    -0.08
    èµ·æŃ¥
    -0.08
    éro
    -0.08
    èĪĮ头
    -0.08
    å±ĭéĩĮ
    -0.08
    å¾ĢæĿ¥
    -0.08
    POSITIVE LOGITS
    è¯ģå®ŀ
    0.14
    æ³Ħéľ²
    0.12
    çĮľæµĭ
    0.11
    é¢ĦåijĬ
    0.11
    çĪĨæĸĻ
    0.11
    æݨæµĭ
    0.11
    æ³Ħæ¼ı
    0.10
    æ¼ı
    0.10
    éĢıéľ²
    0.10
    æ¶Īæģ¯
    0.10
    Activations Density 0.395%

    No Known Activations