© 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. 33562
    Prev
    Next
    INDEX
    Explanations

    change to specified

    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
    otron
    -0.10
    otime
    -0.10
    线索
    -0.10
     Pale
    -0.10
    itar
    -0.09
    ãģ²ãģ¨
    -0.09
     WTF
    -0.09
    çłĴ
    -0.09
    REM
    -0.09
    åIJĦè¡ĮåIJĦä¸ļ
    -0.09
    POSITIVE LOGITS
    æį¢äºĨ
    0.13
    æĶ¹åıĺäºĨ
    0.11
    主æĦı
    0.11
    (change
    0.10
    å·¥ä½ľä½ľé£İ
    0.10
     leopard
    0.10
     Äijá»ķi
    0.10
    à¹ģà¸Ľà¸¥
    0.10
    éĿ¢è²Į
    0.09
     fortunes
    0.09
    Activations Density 0.330%

    No Known Activations