© 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. 11393
    Prev
    Next
    INDEX
    Explanations

    first come first serve

    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
    æŶåħī
    -0.10
    æĶ¹éĿ©åĪĽæĸ°
    -0.09
    é²ľæĺİ
    -0.09
    æĥ³æī¾
    -0.09
    å¼ij
    -0.09
    çļĦæĹ¥
    -0.09
    unta
    -0.08
    æī¾ä¸įåĪ°
    -0.08
    çĭ¬èĩª
    -0.08
    /fire
    -0.08
    POSITIVE LOGITS
    CTS
    0.09
    ä¸įå¿ĺ
    0.08
    PathParam
    0.08
     prob
    0.08
    为äºĨæĽ´å¥½
    0.08
    åĵij
    0.08
    anche
    0.08
     hÆ°á»Łng
    0.08
    ãģĿãģĨãģ§
    0.07
    (GL
    0.07
    Activations Density 0.096%

    No Known Activations