© 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. 23998
    Prev
    Next
    INDEX
    Explanations

    separators followed by values

    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
    iou
    -0.10
    象
    -0.09
    é¾Ħ
    -0.09
    tas
    -0.09
    究竣
    -0.09
    åķ¸
    -0.09
    太å¤ļçļĦ
    -0.08
    ä¸įä»ħèĥ½
    -0.08
    çłĶ究表æĺİ
    -0.08
    åı£å¾Ħ
    -0.08
    POSITIVE LOGITS
    ä¸įåĩºæĿ¥
    0.09
    ç½ijéĢļ
    0.09
    èĵij
    0.08
    让人
    0.08
    饵
    0.08
    icios
    0.08
    é¡ĺ
    0.08
    pora
    0.08
    oter
    0.08
    说çĿĢ
    0.08
    Activations Density 0.268%

    No Known Activations