© 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. 54653
    Prev
    Next
    INDEX
    Explanations

    one could

    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
     ì§Ī
    -0.08
    说çļĦæĺ¯
    -0.08
    æĽī
    -0.08
    hek
    -0.08
    füh
    -0.08
    为äºĨ让
    -0.08
    Ã¶ÄŁ
    -0.08
    æĿ¥åĪ°äºĨ
    -0.07
    渺
    -0.07
    ä¸įç»ıæĦı
    -0.07
    POSITIVE LOGITS
    大çīĩ
    0.09
    oter
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    åŁł
    0.08
     âĢķ
    0.08
    æ¯ĶåĪ©
    0.08
    tier
    0.08
    Õ¿
    0.08
    ç¼
    0.08
     trous
    0.08
    Activations Density 1.617%

    No Known Activations