© 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. 9675
    Prev
    Next
    INDEX
    Explanations

    allows, means, enables

    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
    è¿Ļæł·ä¸ĢæĿ¥
    -0.09
    æµį
    -0.09
    å°ıé¢Ŀ
    -0.08
    åĽŀæĿ¥
    -0.08
    å®ļéĩı
    -0.08
    å¢Ł
    -0.08
    ä¸Ģåij³
    -0.08
    妫
    -0.08
    å·¥ä¸ļåĮĸ
    -0.08
    人çļĦ
    -0.08
    POSITIVE LOGITS
    使åħ¶
    0.17
    让å®ĥ
    0.16
    对åħ¶è¿Ľè¡Į
    0.13
    使ä¹ĭ
    0.13
    æĬĬå®ĥ
    0.12
    å®ĥåı¯ä»¥
    0.11
    å®ĥ
    0.11
    å°Ĩåħ¶
    0.11
    ä»ĸä»¬åľ¨
    0.11
    å®ĥæĺ¯
    0.11
    Activations Density 0.093%

    No Known Activations