© 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. 27365
    Prev
    Next
    INDEX
    Explanations

    claim disclaimer copyright

    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
    ropp
    -0.09
    æ³ķ令
    -0.08
    åĿ¦
    -0.08
    温æļĸ
    -0.08
    .eth
    -0.08
     ethics
    -0.08
    å°ļ
    -0.08
    åıĺå¾ĹæĽ´
    -0.08
    æ¯ķç«Ł
    -0.08
    æµģ
    -0.08
    POSITIVE LOGITS
    对æѤ
    0.09
    åħ¨äº§ä¸ļéĵ¾
    0.09
    éĥ¨åĪĨåľ°åĮº
    0.09
    asil
    0.09
     ÐľÐµÐ¶Ð´Ñĥ
    0.09
    è¿IJ
    0.08
    æ¯ıéĢ¢
    0.08
    tea
    0.08
    讳
    0.08
    sez
    0.08
    Activations Density 0.019%

    No Known Activations