© 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. 55049
    Prev
    Next
    INDEX
    Explanations

    star names and appearances

    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·¯ä¸Ĭ
    -0.10
    æĪĸèĢħ说
    -0.10
    çī¹åĪ«æĺ¯
    -0.08
    ãģ¿ãģª
    -0.08
     handicap
    -0.08
    çļĦéľĢæ±Ĥ
    -0.08
    俨
    -0.08
    åĺļ
    -0.08
    建çŃijéĿ¢ç§¯
    -0.08
     Sok
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.10
    å¯ĵ
    0.09
    éĹ¹
    0.09
    /includes
    0.09
    åŁŁ
    0.09
    å³Ļ
    0.09
    ORED
    0.08
    ç¿ķ
    0.08
    alsa
    0.08
    äºĨå¤ļå°ij
    0.08
    Activations Density 1.164%

    No Known Activations