© 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. 60981
    Prev
    Next
    INDEX
    Explanations

    software development and studios

    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
    åĽ´è§Ĥ
    -0.09
    vern
    -0.09
    æĿĥå¨ģ
    -0.09
    åıĺè¿ģ
    -0.09
    uhn
    -0.09
    奸
    -0.09
    å¦Ĩ
    -0.08
    è°ĥæݧ
    -0.08
     wrink
    -0.08
    让人们
    -0.08
    POSITIVE LOGITS
    å¼Ģåıij
    0.16
    å¼Ģåıij建设
    0.13
    éĸĭçĻ¼
    0.11
    åĪ¶ä½ľ
    0.11
     ÑģÑĤÑĥд
    0.11
    软件
    0.11
    å¼ĢåıijèĢħ
    0.10
    studio
    0.10
    å·¥ä½ľå®¤
    0.10
    .builders
    0.10
    Activations Density 0.283%

    No Known Activations