© 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. 63299
    Prev
    Next
    INDEX
    Explanations

    affirmative action

    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
    æĹłç¼Ŀ
    -0.12
    æīģ
    -0.10
    æĪij们åºĶ该
    -0.10
    é£İçŃĿ
    -0.10
    éĢIJ
    -0.10
    è¹Ĭ
    -0.10
    urer
    -0.10
    åıĽ
    -0.09
    ä¹īåĬ¡
    -0.09
     Brands
    -0.09
    POSITIVE LOGITS
    ç¥
    0.09
    tec
    0.09
    åºĶèģĺ
    0.09
    quals
    0.09
    åİŁæłĩé¢ĺ
    0.09
    atr
    0.09
    ATS
    0.08
    åĪĨæķ°çº¿
    0.08
    é¢ł
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    Activations Density 0.084%

    No Known Activations