© 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. 32715
    Prev
    Next
    INDEX
    Explanations

    in various

    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
    货车
    -0.10
    eg
    -0.09
    éģį
    -0.09
    _gpu
    -0.09
    umpy
    -0.09
     Bro
    -0.08
    è´Ń车
    -0.08
     ê²ĥìľ¼ë¡ľ
    -0.08
    æ®
    -0.08
    iat
    -0.08
    POSITIVE LOGITS
    è¿Ļå¼ł
    0.10
    åºĵåŃĺ
    0.08
     Harding
    0.08
    è¿ĽæĿ¥
    0.08
    åľ¨ä¸Ģ
    0.08
    æĬµæĬĹåĬĽ
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    pb
    0.08
    å¿Ĺ
    0.08
    æłı
    0.08
    Activations Density 0.189%

    No Known Activations