© 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. 35512
    Prev
    Next
    INDEX
    Explanations

    allows for

    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
    è§ģè¿ĩ
    -0.11
    è¯ķåĽ¾
    -0.10
    è¯ķçĿĢ
    -0.10
    èĥ½åģļåĪ°
    -0.10
    ä¼ģåĽ¾
    -0.10
    æİīäºĨ
    -0.10
    è§ļ
    -0.10
    æĹ¥èµ·
    -0.09
     ÑģпоÑĢÑĤ
    -0.09
    è¡®
    -0.09
    POSITIVE LOGITS
    åıijå±ķ空éĹ´
    0.10
    ä¸Ģå®ļç¨ĭ度
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    zza
    0.09
    æľĢ大ç¨ĭ度
    0.09
    å¾Ī好çļĦ
    0.08
    åIJĪçIJĨçļĦ
    0.08
    orc
    0.07
     a
    0.07
     greater
    0.07
    Activations Density 0.010%

    No Known Activations