© 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. 54858
    Prev
    Next
    INDEX
    Explanations

    books and programming languages

    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
    elsing
    -0.08
    侯
    -0.08
    pace
    -0.08
    frei
    -0.08
    å©´
    -0.07
     Ñĩел
    -0.07
    ä¹Łå°±æĺ¯
    -0.07
    åħµé©¬
    -0.07
    aman
    -0.07
    coin
    -0.07
    POSITIVE LOGITS
    æīĭåĨĮ
    0.14
    è¿Ļæľ¬ä¹¦
    0.12
     handbook
    0.11
     Handbook
    0.11
    çļĦç§ĺå¯Ĩ
    0.11
    ä¸Ģæľ¬
    0.11
    ä¸Ľä¹¦
    0.11
    ä¸Ģæľ¬ä¹¦
    0.11
    ãĤ¬ãĤ¤ãĥī
    0.10
     guide
    0.10
    Activations Density 0.254%

    No Known Activations