© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60672
    Prev
    Next
    INDEX
    Explanations

    respond or answer

    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
    Negative Logits
    奢ä¾Ī
    -0.11
    oggled
    -0.10
    åĽłä¸ºä»ĸ
    -0.10
    åĮĻ
    -0.09
    ëŁ¼
    -0.09
    éĺ²æĬ¤
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
     haus
    -0.09
    PROTO
    -0.08
     Advis
    -0.08
    POSITIVE LOGITS
    æ§ģ
    0.10
    çĴł
    0.09
    严å¯Ĩ
    0.08
    chner
    0.08
    HTTPRequest
    0.08
    æİĴéĻ¤
    0.08
    åĢį
    0.08
    ä¸ĸçķĮä¸Ĭ
    0.08
    çłģ
    0.08
    åīįæīĢ
    0.07
    Activations Density 0.006%

    No Known Activations