© 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. 55702
    Prev
    Next
    INDEX
    Explanations

    lists or descriptions of places

    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
    ä¸įç»ı
    -0.10
    河边
    -0.10
    éĥĬåĮº
    -0.10
    å»ī
    -0.10
    ikes
    -0.10
    主è¦ģæľī
    -0.09
    èIJ¥éĢłèī¯å¥½
    -0.09
     Diy
    -0.09
    è¿ĻäºĽéĥ½æĺ¯
    -0.09
    æ¡¢
    -0.09
    POSITIVE LOGITS
    çĤī
    0.10
    çĪIJ
    0.09
    ç¡®
    0.09
    ilename
    0.08
    hte
    0.08
    éħ·
    0.08
    æIJ¬è¿ģ
    0.08
    è¿ģ移
    0.08
    毡
    0.08
    ÙħÙĬÙĦ
    0.08
    Activations Density 0.068%

    No Known Activations