© 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. 58489
    Prev
    Next
    INDEX
    Explanations

    large file size limit

    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
    _PRIORITY
    -0.09
    模ç³Ĭ
    -0.09
     ÐľÐ°
    -0.09
    æĮ¨
    -0.09
    æ¯ıä¸Ģ天
    -0.09
    ÑĦи
    -0.09
    ä¸ĭéĻį
    -0.09
    æİĬ
    -0.09
    å¯ĩ
    -0.09
    çĿ¹
    -0.08
    POSITIVE LOGITS
    -large
    0.11
    _limit
    0.11
    Limit
    0.11
    -long
    0.10
    éķ¿éķ¿çļĦ
    0.10
    æŀģéĻIJ
    0.10
    bons
    0.10
     limit
    0.10
     Limit
    0.10
    éĻIJéĩı
    0.10
    Activations Density 0.352%

    No Known Activations