© 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. 958
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    avn
    -0.09
     ÑĤеÑĩение
    -0.09
    ivo
    -0.08
    è¿Ļä¸ªåľ°æĸ¹
    -0.08
    ihn
    -0.08
    ework
    -0.08
    éķ¿å¯¿
    -0.08
    ä¸įåİ»
    -0.08
    ç¯ĩ
    -0.08
    renc
    -0.08
    POSITIVE LOGITS
     Rupert
    0.10
    ç»Ļä½łä»¬
    0.09
    设æĸ½å»ºè®¾
    0.09
    Props
    0.09
    æľºç»Ħ
    0.09
    ibel
    0.08
    管çIJĨå±Ģ
    0.08
    ãģĮãĤī
    0.08
    ulton
    0.08
    管çIJĨåĴĮ
    0.08
    Activations Density 0.039%

    No Known Activations