© 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. 31289
    Prev
    Next
    INDEX
    Explanations

    your browser

    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
    .ready
    -0.10
    深深çļĦ
    -0.09
    对å¤ĸ
    -0.09
     SALE
    -0.09
    åĽŀçŃĶ
    -0.08
    è¯Ŀ说
    -0.08
    PIPE
    -0.08
     ×ķ×ŀ×Ķ
    -0.08
    éªļ
    -0.08
    讳
    -0.08
    POSITIVE LOGITS
    å¾Ĥ
    0.09
    ä¸ĢåĪĨ
    0.09
    lyn
    0.09
     Summers
    0.09
    casts
    0.09
    åĩĨ
    0.08
    ç¥Ī
    0.08
    管家
    0.08
    bring
    0.08
    ç©¿éĢı
    0.08
    Activations Density 0.001%

    No Known Activations