© 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. 22170
    Prev
    Next
    INDEX
    Explanations

    eyes on or interest in

    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
    å®ī举
    -0.11
    æ±Łæ¹ĸ
    -0.10
    atrix
    -0.10
    æķ·
    -0.09
    _SEG
    -0.09
    åĪĽ
    -0.09
    STRU
    -0.09
    æľĢå¿«
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    ibia
    -0.09
    POSITIVE LOGITS
    å¿ĥ仪çļĦ
    0.18
    å¿ĥ仪
    0.18
    çļĦä¸Ģ款
    0.13
     понÑĢав
    0.13
    å¿ĥåĬ¨
    0.12
    ä¸Ģ款
    0.11
    èĩªå·±åĸľæ¬¢
    0.11
    人éĢī
    0.10
    åIJĪéĢĤçļĦ
    0.10
    åľ¨ç½ijä¸Ĭ
    0.10
    Activations Density 0.074%

    No Known Activations