© 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. 53342
    Prev
    Next
    INDEX
    Explanations

    importance and noting

    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
    lef
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.10
    éĻIJ
    -0.10
    éģĵçIJĨ
    -0.09
    对åħ¶çľŁå®ŀ
    -0.09
    éļ¾éģĵ
    -0.09
    åīĬå¼±
    -0.09
    èĤ¢
    -0.08
    ải
    -0.08
    æī«
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.11
    åĢ¼å¾Ĺ注æĦı
    0.10
    ä¸Ģ件äºĭ
    0.10
    èݺ
    0.09
     notable
    0.09
    clin
    0.09
    ä¹Łå¾Ī
    0.09
    注æĦıåĪ°
    0.09
    éŀł
    0.09
     noting
    0.09
    Activations Density 0.038%

    No Known Activations