© 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. 55679
    Prev
    Next
    INDEX
    Explanations

    to use

    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
    é²ł
    -0.09
    à¹īà¸ĩ
    -0.08
    ÑĤаÑĢ
    -0.08
    åĸľæ¬¢åIJĥ
    -0.08
    é»į
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    åĪĨæĺİ
    -0.07
    ä¸įåľ¨ä¹İ
    -0.07
    èĻĶ
    -0.07
    ä¸įä¿¡
    -0.07
    POSITIVE LOGITS
    使çĶ¨
    0.29
    使çĶ¨çļĦ
    0.25
     use
    0.24
    à¹ĥà¸Ĭ
    0.24
     used
    0.23
     sá»Ń
    0.23
     иÑģполÑĮз
    0.22
    çĶ¨äºĨ
    0.21
     иÑģполÑĮзов
    0.21
    çĶ¨æĿ¥
    0.21
    Activations Density 0.359%

    No Known Activations