© 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. 57305
    Prev
    Next
    INDEX
    Explanations

    award winner

    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
    çłĶ究æīĢ
    -0.11
    é¾Ł
    -0.09
    çļĦæŶåĢĻ
    -0.09
    çĶŁçĶŁ
    -0.09
    ä¸įè¦ģåĨį
    -0.09
    åıijå±ķ空éĹ´
    -0.09
    çªģå¦Ĥåħ¶æĿ¥
    -0.09
    好象
    -0.09
    çļĦåIJĮæŶ
    -0.09
    å¼ķ
    -0.08
    POSITIVE LOGITS
    们
    0.09
    们çļĦ
    0.09
    chap
    0.09
    åĢij
    0.08
    getQuery
    0.08
    UNC
    0.08
    åĴĮ社ä¼ļ
    0.08
    æ¯Ļ
    0.08
    heet
    0.08
    ấ
    0.08
    Activations Density 0.058%

    No Known Activations