© 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. 50562
    Prev
    Next
    INDEX
    Explanations

    go or can't go; tell; buy

    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
    æĬ±
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
    lege
    -0.09
    ä¸Ģ线åŁİå¸Ĥ
    -0.08
    Ron
    -0.08
    (GameObject
    -0.08
    æĦı大
    -0.08
    ince
    -0.08
    foot
    -0.08
    roof
    -0.08
    POSITIVE LOGITS
    太å¤ļçļĦ
    0.09
     redistrib
    0.09
    ä¸ĢåĪĢ
    0.08
    ä¸ŃåĽ½ä¼łç»Ł
    0.08
     Lad
    0.08
    溯
    0.08
    ses
    0.08
    åIJ¬è§ģ
    0.08
    ä¸įåıĺ
    0.08
    代表çĿĢ
    0.08
    Activations Density 0.005%

    No Known Activations