© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    缮çļĦåľ¨äºİ
    -0.10
    æĪĸèĢħ说
    -0.08
    æłª
    -0.08
    追
    -0.08
    ãģ§ãģĤãĤįãģĨ
    -0.08
    ali
    -0.08
     ALSO
    -0.08
    å°±æĺ¯ä¸ºäºĨ
    -0.08
    NESS
    -0.08
    лÑİ
    -0.07
    POSITIVE LOGITS
    äºĨè§£æĽ´å¤ļ
    0.13
    èİ·å¾Ĺ
    0.12
    çį²å¾Ĺ
    0.12
    èİ·å¾ĹæĽ´å¤ļ
    0.11
     yourself
    0.11
    èİ·
    0.11
    便åı¯
    0.11
    享åıĹ
    0.10
    便ä¼ļ
    0.10
    çĽĺ
    0.10
    Activations Density 0.050%

    No Known Activations