© 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. 61482
    Prev
    Next
    INDEX
    Explanations

    to give or show

    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
    ular
    -0.08
    åIJŀ
    -0.07
    ä¸Ģé¡¿
    -0.07
    æŁIJç§įç¨ĭ度
    -0.07
    ä¾ĥ
    -0.07
     Thur
    -0.07
    ç»ıèIJ¥æ¨¡å¼ı
    -0.07
     minValue
    -0.07
     (
    -0.07
     I
    -0.07
    POSITIVE LOGITS
    滥
    0.12
    èĭĶ
    0.11
    éģģ
    0.10
    侬
    0.10
     Dalton
    0.10
    éĹª
    0.10
    ätt
    0.09
    WISE
    0.09
    梧
    0.09
    åį§
    0.09
    Activations Density 0.188%

    No Known Activations