© 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. 55466
    Prev
    Next
    INDEX
    Explanations

    pervasive

    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
    sg
    -0.10
    sha
    -0.10
    _TER
    -0.09
    olle
    -0.09
    sc
    -0.08
    nga
    -0.08
    é½IJåħ¨
    -0.08
     ngủ
    -0.08
    èķī
    -0.08
    踵
    -0.08
    POSITIVE LOGITS
    åħ¨ç¤¾ä¼ļ
    0.10
    ../../
    0.09
    ä¸ĢèĤ¡
    0.09
    æĢ§çĸ¾çĹħ
    0.09
    ../../../
    0.09
    两åı¥
    0.09
    ules
    0.09
     throughout
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
    ä¸įåłª
    0.08
    Activations Density 0.011%

    No Known Activations