© 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. 31990
    Prev
    Next
    INDEX
    Explanations

    lead, Pb

    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
    åģļåĪ°äºĨ
    -0.10
    åįķ身
    -0.10
    èĮ¹
    -0.10
    à´³
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    ãĥĵãĥ«
    -0.09
     اÙĦÙħÙĤ
    -0.09
    UIT
    -0.09
    engl
    -0.09
    åĨ¢
    -0.09
    POSITIVE LOGITS
    4
    0.09
    è¿ģ移
    0.09
    raz
    0.08
    饧
    0.08
    ages
    0.08
     trace
    0.08
    ÑĢем
    0.08
    åIJĪæł¼
    0.08
    8
    0.08
    6
    0.08
    Activations Density 0.076%

    No Known Activations