© 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. 62016
    Prev
    Next
    INDEX
    Explanations

    daily, weekly, or news updates

    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
    å½ĵåľº
    -0.11
     Ñģезон
    -0.11
    errat
    -0.10
    山路
    -0.09
    èŁĨ
    -0.09
    仲
    -0.09
    à¸ķาย
    -0.09
    æ¯ı次éĥ½
    -0.08
    åİĿ
    -0.08
    æľ¬èº«
    -0.08
    POSITIVE LOGITS
    精彩
    0.11
    åİŁåĪĽ
    0.09
    æĻ¨æĬ¥
    0.09
    çij¾
    0.09
    umm
    0.08
    éĬ®
    0.08
     fres
    0.08
    èµ·åºĬ
    0.08
    rece
    0.08
    æݨéĢģ
    0.08
    Activations Density 0.029%

    No Known Activations