© 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. 52703
    Prev
    Next
    INDEX
    Explanations

    to some degree

    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
    éĺģ
    -0.10
    SHOT
    -0.09
     french
    -0.09
    åIJijä¸Ĭ
    -0.09
     Holden
    -0.09
    æĹ©æĹ©
    -0.08
     Tough
    -0.08
    eger
    -0.08
    lá
    -0.08
     Away
    -0.08
    POSITIVE LOGITS
    ç¨ĭ度
    0.26
    çļĦç¨ĭ度
    0.25
     extent
    0.20
    ä¸Ģå®ļç¨ĭ度
    0.18
    ä¸įåIJĮç¨ĭ度
    0.17
     degree
    0.16
    extent
    0.16
    å¾Ī大ç¨ĭ度
    0.16
    æŁIJç§įç¨ĭ度
    0.15
    çļĦåľ°æŃ¥
    0.14
    Activations Density 0.056%

    No Known Activations