© 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. 2988
    Prev
    Next
    INDEX
    Explanations

    non-

    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¸įåłª
    -0.10
    ä¸į说
    -0.10
     Schl
    -0.09
    ä¸įåĨįæĺ¯
    -0.09
    ä¸įçŁ¥ä¸įè§ī
    -0.09
     undis
    -0.09
    antan
    -0.09
    lew
    -0.09
    edia
    -0.09
    ä¸įæĩĪ
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.11
    ä¹Łä¸įåı¯èĥ½
    0.11
    ä¹ŁæĹłæ³ķ
    0.10
    мÑı
    0.09
    olan
    0.08
    å®ŀè´¨
    0.08
    ä¹Łä¸įä¼ļ
    0.08
    .uf
    0.08
    ÑģÑı
    0.08
     nor
    0.08
    Activations Density 0.158%

    No Known Activations