© 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. 50063
    Prev
    Next
    INDEX
    Explanations

    web page file extensions

    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
    æĢ§å¼º
    -0.09
     pl
    -0.09
    åīĮ
    -0.08
    çļĦå¿ĥ
    -0.08
    bul
    -0.08
    less
    -0.08
    irror
    -0.08
     Serialized
    -0.08
    鸦
    -0.07
     tl
    -0.07
    POSITIVE LOGITS
    è¿Ļ个ä¸ĸçķĮ
    0.10
    èij«
    0.10
     trustworthy
    0.10
    ftware
    0.09
    ä¼ļ导èĩ´
    0.09
    uchar
    0.09
    UsageId
    0.09
    ìŀĩ
    0.09
    大家åı¯ä»¥
    0.09
    oupper
    0.09
    Activations Density 0.252%

    No Known Activations