© 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. 56244
    Prev
    Next
    INDEX
    Explanations

    U.S. or India

    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
    æľ¬ç½ijç«Ļ
    -0.11
    è¿Ļæł·æīįèĥ½
    -0.09
    çIJĨäºĭ
    -0.08
    为客æĪ·
    -0.08
    noinspection
    -0.07
    spo
    -0.07
    æĹħ游度åģĩ
    -0.07
    ä¸įåľ¨ä¹İ
    -0.07
    singular
    -0.07
    eme
    -0.07
    POSITIVE LOGITS
    mlink
    0.10
    è¿Ļä¹Łæĺ¯
    0.09
    ánÃŃ
    0.09
    è¿Ľä¸ĢæŃ¥
    0.09
    æİ¥çĿĢ
    0.09
    ãģķãĤīãģ«
    0.09
    缸æ¯Ķä¹ĭä¸ĭ
    0.08
    AREST
    0.08
    uxe
    0.08
    继
    0.08
    Activations Density 0.068%

    No Known Activations