© 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. 56500
    Prev
    Next
    INDEX
    Explanations

    staff turnover or changes

    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
    /play
    -0.10
    èĵĵ
    -0.09
    RuleContext
    -0.09
    ijd
    -0.09
    鹿
    -0.09
    _subtype
    -0.09
    é½ij
    -0.09
    _VC
    -0.09
    olle
    -0.09
    subpackage
    -0.09
    POSITIVE LOGITS
    æį¢äºĨ
    0.17
    æį¢
    0.13
    æĽ´æį¢
    0.13
    æıĽ
    0.11
    åıĺæį¢
    0.11
    åıĺåĬ¨
    0.11
    åĬ¨èį¡
    0.11
    é¢ijç¹ģ
    0.10
    æį¢æĿ¥
    0.10
    éĿ¢åŃĶ
    0.10
    Activations Density 0.068%

    No Known Activations