© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    structure, sensor, engine, tissue, chip

    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
    çªħ
    -0.08
     neo
    -0.08
    ä¸į失
    -0.08
    bez
    -0.08
    oho
    -0.08
    odynam
    -0.07
    å¸ĸ
    -0.07
    çķª
    -0.07
     gal
    -0.07
    åı¯è¡Į
    -0.07
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.10
    åľĪåŃIJ
    0.09
    gos
    0.09
    ä¸ĵ人
    0.09
    CHANT
    0.09
    kim
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
     اÙĦÙħشارÙĥØ©
    0.09
    è¿©
    0.09
     اÙĦÙħÙĪجÙĪدة
    0.08
    Activations Density 0.227%

    No Known Activations