© 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. 56094
    Prev
    Next
    INDEX
    Explanations

    professional services

    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
    å½ĵæĻļ
    -0.09
    æ½ĩ
    -0.09
    éĻī
    -0.09
    åįģ足
    -0.09
    udu
    -0.09
    æĢ§åij½
    -0.08
    æĿ¾å¼Ľ
    -0.08
    麻辣
    -0.08
    ARTH
    -0.08
    主宰
    -0.08
    POSITIVE LOGITS
    çľ¼çĿĽ
    0.08
    éĩįå¿ĥ
    0.08
    麼
    0.08
    зов
    0.08
    è¯ķ
    0.08
    èĦijåŃIJéĩĮ
    0.08
     opponent
    0.08
    YST
    0.08
    讲æķħäºĭ
    0.08
    __,__
    0.08
    Activations Density 0.189%

    No Known Activations