© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37782
    Prev
    Next
    INDEX
    Explanations

    you see

    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
    壬
    -0.08
    èĩ»
    -0.08
    å¼ĢçĿĢ
    -0.08
    贯穿
    -0.08
    çļĦä¸ĢéĿ¢
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
     Invest
    -0.07
    æī©
    -0.07
     Bearing
    -0.07
    祺
    -0.07
    POSITIVE LOGITS
    èĭ¦èĭ¦
    0.11
    è·Łä½ł
    0.10
    åijĬè¯īä½ł
    0.09
    æĹ¥æĬ¥ç¤¾
    0.09
    ä¸Ģç¬Ķ
    0.09
    ä¸ºä½ł
    0.09
    UPI
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    pare
    0.09
    stk
    0.08
    Activations Density 0.064%

    No Known Activations