© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20891
    Prev
    Next
    INDEX
    Explanations

    index-books, General, Calendar, Category, form-pw

    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
    æĭ¿æĿ¥
    -0.09
    è§
    -0.09
    大è¡Ĺ
    -0.09
    WithTitle
    -0.09
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    opal
    -0.09
    ANCH
    -0.09
    ä¸ĢéĿ¢
    -0.09
    éĽĨåĽ¢åħ¬åı¸
    -0.08
    èĢģ人家
    -0.08
    POSITIVE LOGITS
    ฯ
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.09
    orts
    0.09
    ãĤĥ
    0.09
    æ®ĭçĸ¾
    0.08
    ething
    0.08
    ä¸Ģ个éĩįè¦ģ
    0.08
    æ°ijéĹ´
    0.08
    æľīå¤ļå°ij
    0.08
    ãģ«ãģĬãģijãĤĭ
    0.08
    Activations Density 0.443%

    No Known Activations