© 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. 51379
    Prev
    Next
    INDEX
    Explanations

    removing or revealing clothing

    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
    æĺĶ
    -0.09
    缯
    -0.09
     вÑĭп
    -0.09
    ç½Ķ
    -0.09
    åŁºéĩij份é¢Ŀ
    -0.09
    ÙĪÙģ
    -0.08
     ADA
    -0.08
    èİ·åĪ©
    -0.08
    èĪ´
    -0.08
    æĺ¨
    -0.08
    POSITIVE LOGITS
    便äºİ
    0.10
    çķĻä½ı
    0.10
    让
    0.09
    æİīäºĨ
    0.09
    acha
    0.09
    ings
    0.08
    äº®çĽ¸
    0.08
    æİī
    0.08
    åĮĹ京大åѦ
    0.08
    请大家
    0.08
    Activations Density 0.028%

    No Known Activations