© 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. 38401
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    æ³Į
    -0.11
    èĪģ
    -0.10
    SECRET
    -0.09
    年以æĿ¥
    -0.09
    æł·
    -0.09
    å®ģæĦ¿
    -0.09
    è¡Ĺä¸Ĭ
    -0.09
    æķ°çĻ¾
    -0.09
    æ¬ºè´Ł
    -0.09
     cuckold
    -0.08
    POSITIVE LOGITS
    mond
    0.09
    uni
    0.09
    纯
    0.09
    ming
    0.09
    sti
    0.08
    wap
    0.08
    ypes
    0.08
    ÑĢаÑģÑĤ
    0.08
    wald
    0.08
    enth
    0.08
    Activations Density 0.050%

    No Known Activations