© 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. 29681
    Prev
    Next
    INDEX
    Explanations

    would, could, might actions

    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
    åı¯è°ĵ
    -0.11
    妳
    -0.10
    åı¯ä»¥è¯´æĺ¯
    -0.09
    à¹Īะ
    -0.09
    edom
    -0.09
    ä¼ĹæīĢ
    -0.09
    æĻºåķĨ
    -0.09
    itos
    -0.09
    æ¯Ķäºļ
    -0.09
    EventArgs
    -0.09
    POSITIVE LOGITS
    带走
    0.09
    çķĪ
    0.08
    ibil
    0.08
    nel
    0.08
    æĺ¯ä¸ª
    0.08
    èĸ°
    0.08
    ç½¢äºĨ
    0.07
    aler
    0.07
    åĸľå¥½
    0.07
    ãģªãģĦãģ§ãģĻ
    0.07
    Activations Density 0.065%

    No Known Activations