© 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. 875
    Prev
    Next
    INDEX
    Explanations

    what if

    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
    åĴ¬
    -0.10
    ç»ıåħ¸çļĦ
    -0.09
    ç¥Ī祷
    -0.09
    åĬłæ²¹
    -0.09
    çļĦç»ıåħ¸
    -0.09
    çļĩåŃIJ
    -0.08
    对çħ§æ£ĢæŁ¥
    -0.08
    æĺı
    -0.08
    avana
    -0.08
    åĵĢ
    -0.08
    POSITIVE LOGITS
    ä¸įä»ħèĥ½
    0.10
    é¢ł
    0.10
    å°ıå·§
    0.10
     возможноÑģÑĤÑĮ
    0.10
    éļ¾éģĵ
    0.09
    说ä¸įå®ļ
    0.09
    æĹ¢çĦ¶
    0.09
     possibility
    0.09
    è¯ķè¯ķ
    0.09
    èĥ½ä¸įèĥ½
    0.09
    Activations Density 0.133%

    No Known Activations