© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    robot, bot, AI constructs

    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
    çĺ´
    -0.10
    åİ¥
    -0.09
     Blind
    -0.09
    çĸ¾
    -0.09
    è°ĭåĪĴ
    -0.09
    éģ®
    -0.09
    æĬĹæĭĴ
    -0.09
    举æĸ¹
    -0.08
    itage
    -0.08
    稳åģ¥
    -0.08
    POSITIVE LOGITS
    æľºåĻ¨äºº
    0.12
     Watson
    0.10
    人工æĻºèĥ½
    0.10
    é¦Ĵ头
    0.10
     robot
    0.10
    bot
    0.10
    深交
    0.10
    棰
    0.09
    robot
    0.09
    obot
    0.09
    Activations Density 0.116%

    No Known Activations