© 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. 6438
    Prev
    Next
    INDEX
    Explanations

    world that is

    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
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.11
    éģIJ
    -0.09
    åľ¨ç¾İåĽ½
    -0.09
    æĹģ
    -0.09
    éĻĮ
    -0.09
    å¼Ľ
    -0.09
    çļĦéĤ£ç§į
    -0.09
    åĬ«
    -0.08
    éĤ£ç§į
    -0.08
    æ¯Ķè¾ĥå¤ļ
    -0.08
    POSITIVE LOGITS
    éĺij
    0.09
    ä¸ŃåĽ½çī¹èī²
    0.09
    ãģ¯ãģļ
    0.08
    feld
    0.08
    æĪIJ为ä¸ĢåIJį
    0.08
    è¿Ļç¯ĩ
    0.08
    ä¸ĩ家
    0.08
    efore
    0.08
    ei
    0.08
    preview
    0.08
    Activations Density 0.028%

    No Known Activations