© 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. 1542
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    ç½²
    -0.12
    åľ¨æĹ¥æľ¬
    -0.09
    æīĵäºĨ
    -0.09
    è¾Ľ
    -0.08
    ç§
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
     ÑħозÑıйÑģÑĤв
    -0.08
    _almost
    -0.08
    isd
    -0.08
    åŀĴ
    -0.08
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.10
    aklı
    0.09
    å°ģ
    0.08
     stuff
    0.08
    æĸ°å¾ģç¨ĭ
    0.08
     stray
    0.08
    é¼İ
    0.08
    0.08
    侪
    0.08
    osen
    0.08
    Activations Density 0.082%

    No Known Activations