© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47400
    Prev
    Next
    INDEX
    Explanations

    Game Boy colors

    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
    Negative Logits
     comps
    -0.09
    лиÑĨ
    -0.09
    oop
    -0.09
    æĸ°äºº
    -0.09
    /renderer
    -0.09
    èķ¾
    -0.08
    angu
    -0.08
    éĥ½è§īå¾Ĺ
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
    irut
    -0.08
    POSITIVE LOGITS
    é¢Ħæ¡Ī
    0.11
    æ¯ĹéĤ»
    0.09
    èĭģ
    0.09
    ä¸Ģåī¯
    0.09
    èĩ´çĻĮ
    0.09
    åį®
    0.08
    ä¸įè§ģ
    0.08
    æīĵçĿĢ
    0.08
    ä¼Ļ
    0.08
    åķĦ
    0.08
    Activations Density 0.001%

    No Known Activations