© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20522
    Prev
    Next
    INDEX
    Explanations

    educational students

    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
    æŀ£
    -0.09
    åĪ¨
    -0.09
    æ²¥
    -0.08
    èĤ²
    -0.08
    uming
    -0.08
     verk
    -0.08
    FA
    -0.08
    骢
    -0.07
     ripe
    -0.07
    optim
    -0.07
    POSITIVE LOGITS
    åĮ»åѦéĻ¢
    0.10
     guesses
    0.09
    åĥŃ
    0.09
    å¼ĢåѦ
    0.09
    eof
    0.09
    åįľ
    0.09
    ç¾ŀ
    0.09
    -educated
    0.09
    åĤħ
    0.09
    çŃīè¡Įä¸ļ
    0.09
    Activations Density 0.202%

    No Known Activations