© 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. 50645
    Prev
    Next
    INDEX
    Explanations

    forms and IRS documents

    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
    åľ°åĿª
    -0.10
    éªħ
    -0.10
    èĭij
    -0.09
    é»Ħå±±
    -0.09
    éĻ¡
    -0.09
     pear
    -0.09
     ÑĤоÑĩки
    -0.09
     Wend
    -0.09
    Resolved
    -0.08
    为æ°ij
    -0.08
    POSITIVE LOGITS
    æĬ¥éĢģ
    0.15
    å¡«åĨĻ
    0.13
    å¡«æĬ¥
    0.12
    ä¸Ĭä¼ł
    0.10
     required
    0.09
    æıIJ交
    0.09
     submission
    0.09
     Submission
    0.09
     dreaded
    0.09
    年度
    0.09
    Activations Density 0.093%

    No Known Activations