© 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. 27068
    Prev
    Next
    INDEX
    Explanations

    bands and artists names

    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
     himself
    -0.11
    åIJģ
    -0.09
    è°ħ
    -0.09
    并ä¸į代表
    -0.09
    ä»ĸ对
    -0.08
    -addons
    -0.08
    itt
    -0.08
    æķ´ä¸ªäºº
    -0.08
    ä»ĸèĩªå·±
    -0.08
     pov
    -0.08
    POSITIVE LOGITS
    æĪIJåijĺ
    0.10
    ssi
    0.10
     ÙĥاÙĨÙĪا
    0.09
    æĪIJç«ĭ以æĿ¥
    0.09
    eurs
    0.09
    èĻ¹
    0.09
    ä¸Ģ头
    0.08
    秦çļĩ
    0.08
    naires
    0.08
    members
    0.08
    Activations Density 0.040%

    No Known Activations