© 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. 22566
    Prev
    Next
    INDEX
    Explanations

    interested in

    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
    足迹
    -0.09
    轨
    -0.09
    缮çļĦ
    -0.09
    槿
    -0.09
    æļ´éĽ¨
    -0.09
    nyder
    -0.09
    åIJĮæĥħ
    -0.09
     пÑĢакÑĤи
    -0.08
    æľīæŶ
    -0.08
    åĴĮåľ°åĮº
    -0.08
    POSITIVE LOGITS
     Bark
    0.09
     Minds
    0.09
     Rid
    0.09
    hab
    0.09
    åĪĨæĪIJ
    0.08
    串
    0.08
    åıĤåĬł
    0.08
    ãģĬãģı
    0.08
    åĽ½åĬ¡
    0.08
    _VIRTUAL
    0.08
    Activations Density 0.015%

    No Known Activations