© 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. 30373
    Prev
    Next
    INDEX
    Explanations

    Palmaz, HELLP, cloture

    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
    Y
    -0.08
    åķ·
    -0.08
    çļĦçľ¼
    -0.08
    çļĦ社ä¼ļ
    -0.08
    казаÑĤÑĮ
    -0.08
    (.)
    -0.08
    itr
    -0.07
    åķIJ
    -0.07
    çļĦèĥ½éĩı
    -0.07
    åĸŁ
    -0.07
    POSITIVE LOGITS
    bum
    0.09
    inki
    0.09
    åѤåĦ¿
    0.09
    éļľ
    0.09
    rack
    0.09
    主ç¼ĸ
    0.08
    Ô²
    0.08
     Belle
    0.08
    æĿ¯
    0.08
    ä¹Łä¸įè¦ģ
    0.08
    Activations Density 1.161%

    No Known Activations