© 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. 62952
    Prev
    Next
    INDEX
    Explanations

    in a

    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
    åĬŀäºĭ
    -0.08
    kees
    -0.08
    Ctrl
    -0.08
    ä¸ĭåij¨
    -0.07
    å¤Ļ
    -0.07
    ìĸ¸
    -0.07
     Wy
    -0.07
    åħīéĺ´
    -0.07
     MPs
    -0.07
    MMC
    -0.07
    POSITIVE LOGITS
    大å¤ļæķ°
    0.15
    æĥħåĨµä¸ĭ
    0.14
    çݰ代社ä¼ļ
    0.13
    çİ°å®ŀä¸Ń
    0.12
    大éĥ¨åĪĨ
    0.12
    å¤ļæķ°
    0.12
    åľºåIJĪ
    0.11
    å¾Īå¤ļæŶåĢĻ
    0.10
    çݰ代
    0.10
    å¾Ģå¾Ģ
    0.10
    Activations Density 0.549%

    No Known Activations