© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52688
    Prev
    Next
    INDEX
    Explanations

    past times and events

    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
    azzi
    -0.09
    ä¸ĢæŶ
    -0.09
    lam
    -0.09
    çŃĽ
    -0.08
    缼è¡Į
    -0.08
    repr
    -0.08
    æīĩ
    -0.08
    ä¼łéĢģ
    -0.08
     налиÑĩ
    -0.08
    ä¿®
    -0.07
    POSITIVE LOGITS
    ä¸į让
    0.10
    å¾Ĺèµ·
    0.10
    æĸ°æĪ¿
    0.10
    rades
    0.09
    nable
    0.09
    社ä¼ļ稳å®ļ
    0.09
    åľ¨æĹ¥æľ¬
    0.09
     пÑĢедназ
    0.09
    åIJĦèĩª
    0.09
    ä¸įéĶĪ
    0.09
    Activations Density 0.014%

    No Known Activations