© 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. 19582
    Prev
    Next
    INDEX
    Explanations

    pdf availability and downloads

    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
    VISIBLE
    -0.09
    è¯įæĿ¡
    -0.09
    éĿ
    -0.08
    ascript
    -0.08
    bane
    -0.08
    ä½¥
    -0.08
    æįIJ
    -0.08
    ä¸Ģæľµ
    -0.08
    ç»ıéªĮ
    -0.08
    æīĭ表
    -0.08
    POSITIVE LOGITS
     PDF
    0.13
     pdf
    0.13
    åī¯æľ¬
    0.12
    ä¸Ģ份
    0.11
    PDF
    0.11
    è¿Ļ份
    0.11
    pdf
    0.11
    äºĨä¸Ģ份
    0.11
    æĸĩæľ¬
    0.11
    æ¸ħæĻ°
    0.11
    Activations Density 0.103%

    No Known Activations