© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26709
    Prev
    Next
    INDEX
    Explanations

    flow passage fluid motion

    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
    æ¢ĥ
    -0.10
    ç«ł
    -0.10
    ault
    -0.09
    овал
    -0.09
    ç¿ĺ
    -0.09
    åĽ½å®ī
    -0.09
    æĴij
    -0.09
    çĽĹçªĥ
    -0.08
    ìĬ¨
    -0.08
    åį§å®¤
    -0.08
    POSITIVE LOGITS
    æ°´æµģ
    0.16
    æµģæ°´
    0.14
    èĴ¸æ±½
    0.11
    è½
    0.10
    é£İåIJ¹
    0.10
     sur
    0.10
    人æµģ
    0.10
    æµģéĩı
    0.10
    èĴ¸
    0.09
    _PA
    0.09
    Activations Density 0.105%

    No Known Activations