© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21794
    Prev
    Next
    INDEX
    Explanations

    written documents or text

    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
    游èīĩ
    -0.09
    åľ¨äº¬
    -0.09
    è´´
    -0.08
    coin
    -0.08
    å±
    -0.08
     TM
    -0.08
    å·§åIJĪ
    -0.08
    (TM
    -0.08
    å¼ĢéŨ
    -0.08
    ÑĢÑĥÑĤ
    -0.08
    POSITIVE LOGITS
    书éĿ¢
    0.23
    æĸĩæ¡£
    0.13
    æĸĩåŃĹ
    0.13
     dokument
    0.12
     written
    0.12
    è®°å½ķ
    0.12
    åĨĻä¸ĭ
    0.11
     문ìĦľ
    0.11
     докÑĥменÑĤ
    0.11
    çļĦæĸĩåŃĹ
    0.10
    Activations Density 0.065%

    No Known Activations