© 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. 55876
    Prev
    Next
    INDEX
    Explanations

    you asking for eligibility

    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
    éĻIJå®ļ
    -0.10
    ople
    -0.09
     bac
    -0.08
    dez
    -0.08
    anza
    -0.08
    china
    -0.08
     perse
    -0.07
     Schwarz
    -0.07
    æŶä¸į
    -0.07
    åĨĴçĿĢ
    -0.07
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸Ģ
    0.13
    符åIJĪæĿ¡ä»¶
    0.11
    æĥ³æĥ³
    0.10
    è§īå¾Ĺèĩªå·±
    0.10
    çįł
    0.10
    èģĶç³»æĪij们
    0.10
    稳妥
    0.10
    å¿ĥåĬ¨
    0.09
    ç»ıéªĮ丰å¯Į
    0.09
    人èĦī
    0.09
    Activations Density 0.044%

    No Known Activations