© 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. 49560
    Prev
    Next
    INDEX
    Explanations

    Ballard

    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
    ä»ĸå¦Ī
    -0.11
    å®ĺæĸ¹å¾®åįļ
    -0.10
    æĸĩç«łæĿ¥æºIJ
    -0.10
    гÑĢани
    -0.10
    åįıä¼ļä¼ļéķ¿
    -0.10
    ä»Ĭ天å°ıç¼ĸ
    -0.10
    æ¶İ
    -0.09
    меÑīа
    -0.09
    åīįæīĢæľªæľī
    -0.09
    abox
    -0.09
    POSITIVE LOGITS
     ÑģÑĢазÑĥ
    0.10
    "},{"
    0.09
    åĵŁ
    0.08
    çİĩåħĪ
    0.07
    æŃ¤é¡¹
    0.07
    âľħ
    0.07
    è¿Ļæĺ¯
    0.07
    è¿Ļ个
    0.07
     дейÑģÑĤв
    0.07
    åİĭ
    0.07
    Activations Density 0.708%

    No Known Activations