© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20667
    Prev
    Next
    INDEX
    Explanations

    types and varieties

    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
     passage
    -0.10
     Gol
    -0.09
    åľ°éĿ¢
    -0.09
    æ´¼
    -0.08
    éªļ
    -0.08
     Mirage
    -0.08
     fork
    -0.08
    lette
    -0.08
    ether
    -0.08
    pher
    -0.08
    POSITIVE LOGITS
    TED
    0.10
    atan
    0.10
    æĿ¥è¯´
    0.09
     Woo
    0.09
     extingu
    0.08
    ones
    0.08
    off
    0.08
    ä¾Ĩ說
    0.08
    æĿ¥ä¸įåıĬ
    0.08
    uum
    0.08
    Activations Density 0.138%

    No Known Activations