© 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. 53490
    Prev
    Next
    INDEX
    Explanations

    do have

    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
    /about
    -0.10
    alo
    -0.09
    åį³ä½¿æĺ¯
    -0.09
    ä¸įåĪĨ
    -0.09
     Accord
    -0.08
    amy
    -0.08
    awe
    -0.08
    å¨ģ
    -0.08
    åıĪæĺ¯
    -0.08
    rien
    -0.08
    POSITIVE LOGITS
    æľīä¸ĢäºĽ
    0.11
    æŁIJç§įç¨ĭ度
    0.11
    éĤ£æł·
    0.10
    èĩªæѤ
    0.10
    ä¸įéĶĻçļĦ
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    æľī个
    0.09
     ë§İìĿ´
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    ãģ£ãģ¨
    0.09
    Activations Density 0.054%

    No Known Activations