© 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. 39510
    Prev
    Next
    INDEX
    Explanations

    midfacial, middle, midsection, medium

    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
    ServiceProvider
    -0.09
    è°´
    -0.09
    åĽº
    -0.08
     leo
    -0.08
     пи
    -0.08
    ä¸ĭéĿ¢å°±
    -0.08
    _AUX
    -0.08
    è¾ľ
    -0.08
    оÑĩ
    -0.08
    ëĿ½
    -0.08
    POSITIVE LOGITS
    ä¸ŃéĹ´
    0.12
    åľ°å¸¦
    0.11
    _MAY
    0.10
    ÑİÑĢ
    0.10
    ìķĻ
    0.09
    çªģåĩºéĹ®é¢ĺ
    0.09
    èħ°éĥ¨
    0.09
    ioc
    0.09
    -sized
    0.09
    (mid
    0.09
    Activations Density 0.152%

    No Known Activations