© 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. 4517
    Prev
    Next
    INDEX
    Explanations

    look forward to

    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
    毫ä¸įçĬ¹è±«
    -0.10
    æµģæ°ĵ
    -0.10
    éªĬ
    -0.09
    EGA
    -0.09
    æ·±åħ¥æİ¨è¿Ľ
    -0.09
    EIF
    -0.09
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.09
    éļ¾æ°ij
    -0.09
     Panic
    -0.09
    å¾Īæ·±
    -0.09
    POSITIVE LOGITS
    æ¯ıä¸Ģ次
    0.10
    æĻ¨
    0.09
    æ¯ı次
    0.09
    æ±Łä¸ľ
    0.08
    è°ĥåĬ¨
    0.08
    ocratic
    0.08
    æĥ³æī¾
    0.08
    mere
    0.07
    eness
    0.07
    èİ«è¿ĩäºİ
    0.07
    Activations Density 0.005%

    No Known Activations