© 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. 26270
    Prev
    Next
    INDEX
    Explanations

    pupiform shape

    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
    åħ¨å¥Ĺ
    -0.10
    路人
    -0.10
    rets
    -0.09
    çĵ¦
    -0.09
    reater
    -0.09
    ä¸Ģ年级
    -0.09
    æĦļ
    -0.09
    箪
    -0.09
    è·¯ç¨ĭ
    -0.09
     lá»Ńa
    -0.08
    POSITIVE LOGITS
    æŀķ
    0.09
    _ENTER
    0.09
    ä¸įåıĬ
    0.09
    aday
    0.08
     cust
    0.08
    éĢļä¿Ĺ
    0.08
    æIJĵ
    0.08
    Enumeration
    0.08
    ic
    0.08
    伪
    0.08
    Activations Density 0.057%

    No Known Activations