© 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. 29752
    Prev
    Next
    INDEX
    Explanations

    better than

    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
     Scri
    -0.09
    /her
    -0.09
    æ½¼
    -0.09
    漪
    -0.09
    enga
    -0.09
    illion
    -0.09
    èĤĥ
    -0.08
    ÑĢÑıд
    -0.08
    orem
    -0.08
    é«ĺåİŁ
    -0.08
    POSITIVE LOGITS
    -than
    0.10
    æĶ¿
    0.09
     parts
    0.09
    thest
    0.08
    é£İæĻ¯
    0.08
    rar
    0.08
    ä¸Ģ头
    0.08
    æĽ´éĩįè¦ģçļĦ
    0.08
    姿
    0.07
    é¾Ļæ¹ĸ
    0.07
    Activations Density 0.044%

    No Known Activations