© 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. 48116
    Prev
    Next
    INDEX
    Explanations

    numbers and proper nouns like King

    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
    æħİ
    -0.12
    ä¼ģä¸ļæıIJä¾Ľ
    -0.11
    ä½łèĩªå·±
    -0.10
    èŀºä¸Ŀ
    -0.09
    å·§
    -0.09
    å·Ŀ
    -0.09
    pill
    -0.09
    plx
    -0.09
    鸣
    -0.09
    éģ
    -0.09
    POSITIVE LOGITS
     popularity
    0.14
    人æ°Ķ
    0.12
    åıĹ欢è¿İ
    0.12
    åIJ¸å¼ķäºĨ
    0.12
    3
    0.11
    4
    0.11
     popular
    0.11
    èµ¢å¾ĹäºĨ
    0.11
    5
    0.11
    æİĢèµ·
    0.11
    Activations Density 0.118%

    No Known Activations