© 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. 3411
    Prev
    Next
    INDEX
    Explanations

    browser -UA compatibility

    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
    ç´ĭ
    -0.11
    ç¼Ŀ
    -0.10
    éĻ¡
    -0.10
    纹
    -0.10
    çĸı导
    -0.10
     Astronomy
    -0.09
    éĺ»åĬĽ
    -0.09
    _easy
    -0.09
    太é«ĺ
    -0.09
    istle
    -0.09
    POSITIVE LOGITS
    æµıè§ĪåĻ¨
    0.13
    _browser
    0.13
     browser
    0.11
     browsers
    0.11
    doctype
    0.11
    browser
    0.10
    -browser
    0.10
    .browser
    0.10
     Browser
    0.09
     Chrome
    0.09
    Activations Density 0.396%

    No Known Activations