© 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. 52664
    Prev
    Next
    INDEX
    Explanations

    web links and markup

    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
    æľŁçĽ¼
    -0.10
    .getLine
    -0.10
    .IsMatch
    -0.10
    äºī夺
    -0.09
    æĬ¬
    -0.09
    åĽ½äºº
    -0.09
    ék
    -0.09
    太太
    -0.09
    顶å°ĸ
    -0.08
    ç±³ç²ī
    -0.08
    POSITIVE LOGITS
     Web
    0.11
     Rope
    0.10
    åĪ¶ä½ľ
    0.10
    æ½®
    0.10
     web
    0.10
    Web
    0.09
    éĨĴ缮
    0.09
     units
    0.09
    -web
    0.09
    .Web
    0.08
    Activations Density 0.302%

    No Known Activations