© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    cash gift donations provided

    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
    ç²²
    -0.10
    主è§Ĥ
    -0.10
    èĭĶ
    -0.09
     jeopardy
    -0.08
    uga
    -0.08
    éĤ£ç§į
    -0.08
    è¾Ł
    -0.08
    PCS
    -0.08
    éĤ£æł·çļĦ
    -0.08
    缴è¾ĸ
    -0.08
    POSITIVE LOGITS
    ä¸ĢåIJij
    0.09
     circ
    0.09
    itals
    0.09
    åıªæĥ³
    0.09
    èĴĻ
    0.09
    ÑĮе
    0.08
    ä¸įæĦ¿
    0.08
    mani
    0.08
    /Gate
    0.08
    irts
    0.08
    Activations Density 0.001%

    No Known Activations