© 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. 58211
    Prev
    Next
    INDEX
    Explanations

    JSON/dictionary structure delimiters

    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
    ined
    -0.09
    èĩ³æѤ
    -0.08
    æ¯ĭ
    -0.08
    éĤĵå°ı
    -0.08
    ç¥Ģ
    -0.08
    æĪĸèĢħ说
    -0.08
    æ°Ļ
    -0.07
    æħ¨
    -0.07
    ajar
    -0.07
    ç¥Ń
    -0.07
    POSITIVE LOGITS
    次è¦ģ
    0.09
    æ¯Ľ
    0.09
    绿
    0.08
    æ··åIJĪ
    0.08
    个æĢ§
    0.08
    .GetName
    0.08
    æī«ä¸Ģæī«
    0.08
    aÄŁ
    0.08
    äºĽ
    0.08
     kız
    0.08
    Activations Density 0.188%

    No Known Activations