© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1544
    Prev
    Next
    INDEX
    Explanations

    model and mode

    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
     pret
    -0.10
    å¦Ĩ
    -0.10
    ç¼ķ
    -0.10
    iceps
    -0.09
    é«ĺä¸ŃçĶŁ
    -0.09
    æ¸Ĭ
    -0.09
    æįį
    -0.09
    å®ĺ宣
    -0.09
    ä¹IJæĦı
    -0.09
    æ¯ĶæĪij
    -0.09
    POSITIVE LOGITS
    模å¼ı
    0.17
    åıijå±ķ模å¼ı
    0.15
    迷失
    0.13
    管çIJĨ模å¼ı
    0.12
    æĸ°æ¨¡å¼ı
    0.11
    èĻİ
    0.09
    ç»ıèIJ¥æ¨¡å¼ı
    0.09
     mode
    0.09
    ä¾ĿéĿł
    0.09
    mode
    0.08
    Activations Density 0.046%

    No Known Activations