© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 48613
    Prev
    Next
    INDEX
    Explanations

    activities and hobbies

    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
    éĿĴæĺ¥
    -0.11
    ãģ£ãģįãĤĬ
    -0.09
    为主çļĦ
    -0.09
     slideshow
    -0.08
    ãģ¤ãģį
    -0.08
    æľ¬æ¬¡
    -0.08
    ä¸įåħį
    -0.08
    åΰè¿ĻéĩĮ
    -0.08
    åĨįåΰ
    -0.08
    é¦Ĵ头
    -0.08
    POSITIVE LOGITS
    æĪijåĸľæ¬¢
    0.11
    æıŃ
    0.10
    åIJ¦
    0.10
    سÙģ
    0.10
    çļĦæĢ§æł¼
    0.09
    æ¯ı个æľĪ
    0.09
    笺
    0.09
    æ±Ľ
    0.09
    azen
    0.08
    å°¤
    0.08
    Activations Density 0.065%

    No Known Activations