© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38146
    Prev
    Next
    INDEX
    Explanations

    people in roles or with specific suffixes

    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
    æĺ¯æĪij们
    -0.10
    æīįæĺ¯çľŁæŃ£
    -0.09
    éĥ½èĥ½
    -0.08
    .misc
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    æ°ijæĦı
    -0.08
    å²ģ以ä¸ĭ
    -0.08
    çĹķ
    -0.08
    å¦ĤæŀľæĪij们
    -0.08
    æ¦ľ
    -0.07
    POSITIVE LOGITS
    纷纷
    0.10
    หว
    0.09
    ä¸Ģèĩ´
    0.09
    奴
    0.09
    uez
    0.09
     rev
    0.09
    rant
    0.09
    rev
    0.09
    éĥ½è§īå¾Ĺ
    0.09
    ä¸ĢåĪĻ
    0.09
    Activations Density 0.101%

    No Known Activations