© 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. 56251
    Prev
    Next
    INDEX
    Explanations

    .cookies

    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
    åį´åıijçİ°
    -0.09
    è¯Ĩ
    -0.08
    产åĩº
    -0.08
    çŁ
    -0.08
    åľ¨å®¶éĩĮ
    -0.08
    .tif
    -0.08
    ä¹Łå°±æĺ¯
    -0.07
    åĶĽ
    -0.07
    âĢij
    -0.07
    .jpeg
    -0.07
    POSITIVE LOGITS
    èĥ¸
    0.10
    zik
    0.09
    åģĮ
    0.09
    .cookies
    0.09
    _ob
    0.09
    éļ¼
    0.09
    ç»Ģ
    0.09
    åĵ¨
    0.09
    coat
    0.09
    åı¸ä»¤
    0.09
    Activations Density 0.114%

    No Known Activations