© 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. 22436
    Prev
    Next
    INDEX
    Explanations

    Garmin, Wiley, Wiggins, Lenovo, Dummies

    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
     Bek
    -0.10
    bred
    -0.09
    è¿ĻçĤ¹
    -0.09
    ç«Łæĺ¯
    -0.09
    alli
    -0.09
    è¾ŀ
    -0.09
    пÑĥÑģ
    -0.08
    rella
    -0.08
     Organizer
    -0.08
    ãĥĹãĥ©ãĤ¤
    -0.08
    POSITIVE LOGITS
    ãģŀ
    0.09
    -Aug
    0.08
    uml
    0.08
    ä¸į太
    0.08
    åĤ»
    0.08
    çģ¼
    0.08
    utes
    0.08
    sar
    0.08
    人家
    0.08
    MUX
    0.08
    Activations Density 0.012%

    No Known Activations