© 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. 55440
    Prev
    Next
    INDEX
    Explanations

    winning matches, tournaments, or series

    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
    ä¹ħäºĨ
    -0.08
    erten
    -0.08
    å¿łè¯ļ
    -0.08
    fuck
    -0.07
     arisen
    -0.07
    instr
    -0.07
    ä½İ头
    -0.07
     HACK
    -0.07
    èµ·æĿ¥äºĨ
    -0.07
    gone
    -0.07
    POSITIVE LOGITS
    å¾¼
    0.11
    strar
    0.09
    irut
    0.09
    ä¸Ģ举
    0.09
    ä¸ĢåĪĨ
    0.09
    éĩįè¦ģåĽłç´ł
    0.09
    .setInput
    0.09
    çѵ
    0.08
    âu
    0.08
    ⾧
    0.08
    Activations Density 0.060%

    No Known Activations