© 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. 57826
    Prev
    Next
    INDEX
    Explanations

    mine, yours

    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
    å¾Ĺ罪
    -0.08
    æİĮæı¡äºĨ
    -0.08
    ç±
    -0.08
    æİĮæı¡
    -0.08
    æľīæīĢ
    -0.08
    æ²¥
    -0.08
     ze
    -0.08
    鼩
    -0.08
    身份
    -0.07
    аÑĩ
    -0.07
    POSITIVE LOGITS
    æĪijä¹Ł
    0.12
    ä½ľèĢħæľ¬äºº
    0.11
    mine
    0.10
    æŃĨ
    0.10
     mine
    0.10
    æĪijèĩªå·±
    0.10
    éĻĦ
    0.09
    ç§ģãĤĤ
    0.09
    æľ¬æĬ¥
    0.09
    полн
    0.09
    Activations Density 0.161%

    No Known Activations