© 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. 32244
    Prev
    Next
    INDEX
    Explanations

    names followed by last names

    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
    丰满
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    ç»ĻäºĨæĪij
    -0.09
    èī¯
    -0.09
    æĪij家
    -0.08
    íĮ¨
    -0.08
    é¢Ĩ导çıŃåŃIJ
    -0.08
    åģļæ³ķ
    -0.08
    对æĪij们
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.12
    æĹ¥æĬ¥éģĵ
    0.11
    è®°èĢħ
    0.10
    éĩĩ访
    0.10
    åİŁæłĩé¢ĺ
    0.09
    éĢļ讯åijĺ
    0.09
    æĶ»åĬ¿
    0.09
    _WP
    0.09
    è®°èĢħäºĨ解
    0.09
    _coverage
    0.09
    Activations Density 0.114%

    No Known Activations