© 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. 62458
    Prev
    Next
    INDEX
    Explanations

    gave up paying

    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
    èµ·æĿ¥
    -0.10
     Bare
    -0.09
    æĸ¹åı¯
    -0.09
    nip
    -0.09
     PyErr
    -0.09
    exit
    -0.09
     OPP
    -0.09
     exiting
    -0.08
    SKIP
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    POSITIVE LOGITS
    äºĨè§£æĽ´å¤ļ
    0.10
    abil
    0.10
     Nicholson
    0.09
    è¿ĻåĿĹ
    0.09
     Nichols
    0.08
    æ±ŁåĮĹ
    0.08
    URN
    0.08
    åĭĥåĭĥ
    0.08
    æĮ£æīİ
    0.08
     idea
    0.08
    Activations Density 0.009%

    No Known Activations