© 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. 18512
    Prev
    Next
    INDEX
    Explanations

    luxury, style, refinement, intelligence

    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
    éģĹçķĻ
    -0.09
    计åħ¥
    -0.09
    侧éĿ¢
    -0.09
    æīª
    -0.09
    å¼ºåĽ½
    -0.08
    uro
    -0.08
    æ»ķ
    -0.08
    èĭ¥å¹²
    -0.08
    èİ·å¾ĹæĽ´å¤ļ
    -0.08
    åı¯ä»¥èİ·å¾Ĺ
    -0.08
    POSITIVE LOGITS
    å·§åIJĪ
    0.10
    oles
    0.09
     awe
    0.09
    kehr
    0.09
    ycin
    0.08
    pliant
    0.08
    严谨
    0.08
    รà¸Ńย
    0.08
    ä¸įéĶĪ
    0.08
    IBC
    0.08
    Activations Density 0.145%

    No Known Activations