© 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. 57161
    Prev
    Next
    INDEX
    Explanations

    value or name in a list

    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
    æĺ¯çĶ¨æĿ¥
    -0.10
    çĶ¨æĿ¥
    -0.09
    ARN
    -0.09
    çĶ±ä¸ŃåĽ½
    -0.08
    æĢ§åĴĮ
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    ç»Ļ人ä¸Ģç§į
    -0.08
    omat
    -0.08
    海绵
    -0.07
    éĸĵãģ«
    -0.07
    POSITIVE LOGITS
    à¹ĥà¸Ļ
    0.17
     ÙģÙĬ
    0.16
     in
    0.16
     trong
    0.15
     ÙģÙī
    0.14
    åľ¨åĨħçļĦ
    0.14
    åľ¨å¸Ĥåľºä¸Ĭ
    0.13
    åľ¨è¿Ļ
    0.13
    åľ¨
    0.13
     в
    0.12
    Activations Density 1.541%

    No Known Activations