© 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. 32748
    Prev
    Next
    INDEX
    Explanations

    people's names and professions

    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
    exc
    -0.09
    审议
    -0.08
    åIJįåĪĹ
    -0.08
    æķĪåĬĽ
    -0.08
    æĪĺçģ«
    -0.08
     consect
    -0.08
    俸
    -0.08
    -exc
    -0.08
    失è°ĥ
    -0.08
    è·Łè¿Ľ
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥
    0.17
    ç¶ĵçĩŁ
    0.14
     businessman
    0.13
    ç»ıèIJ¥èĢħ
    0.13
    ç»ıèIJ¥çIJĨ念
    0.12
    ç»ıèIJ¥æ´»åĬ¨
    0.12
    èĢģæĿ¿
    0.12
     himself
    0.12
    使ä¹ĭ
    0.12
    ç»ıèIJ¥ç®¡çIJĨ
    0.11
    Activations Density 0.131%

    No Known Activations