© 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. 9926
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    产åĢ¼
    -0.09
    çĻ½é¢Ĩ
    -0.09
    åİ¥
    -0.08
    thood
    -0.08
    èĶ·
    -0.08
    icer
    -0.08
    upon
    -0.08
    第äºĮ大
    -0.08
    äºĭå®ľ
    -0.08
    åįłåľ°éĿ¢ç§¯
    -0.08
    POSITIVE LOGITS
    .Pixel
    0.10
    åģıåIJij
    0.09
    yers
    0.09
    ucks
    0.08
    cls
    0.08
    ãĤªãĥ³
    0.08
    igte
    0.08
    æľ¬ç«Ļ
    0.08
    omid
    0.08
    uju
    0.08
    Activations Density 0.002%

    No Known Activations