© 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. 48635
    Prev
    Next
    INDEX
    Explanations

    turbocharged or aspirated engines

    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
    ä»İ严治
    -0.11
    尽头
    -0.11
    atile
    -0.10
    _pars
    -0.10
    éģij
    -0.10
    нÑĮ
    -0.10
    åħ¢
    -0.09
    ç§Ģ丽
    -0.09
    å¹ķåIJİ
    -0.09
    æݾ
    -0.09
    POSITIVE LOGITS
    åĸľ
    0.10
    strup
    0.09
    åºľ
    0.08
    stro
    0.08
     Lomb
    0.08
    åѦä½į
    0.08
    å¿Ļ
    0.08
     обÑĢазом
    0.08
    éļĶçĿĢ
    0.08
    =in
    0.07
    Activations Density 0.064%

    No Known Activations