© 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. 23386
    Prev
    Next
    INDEX
    Explanations

    stage

    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¸ĭå·´
    -0.10
    ä¼ļåIJĮ
    -0.09
    çļĦ带é¢Ĩä¸ĭ
    -0.09
    æľºåĬ¨
    -0.09
    ssize
    -0.08
    athy
    -0.08
    .anim
    -0.08
    ãĤ¢ãĥĭãĥ¡
    -0.08
    åIJĮæĻĤãģ«
    -0.08
    太åIJİ
    -0.08
    POSITIVE LOGITS
    (stage
    0.13
    .Stage
    0.12
    stage
    0.12
     stage
    0.11
    éĺ¶æ®µ
    0.11
    .stage
    0.10
    -stage
    0.10
    lain
    0.10
    峡
    0.10
    onium
    0.10
    Activations Density 0.038%

    No Known Activations