© 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. 38894
    Prev
    Next
    INDEX
    Explanations

    outdated or subject

    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
    åIJĮèĥŀ
    -0.11
     Hilton
    -0.09
    éĢIJ
    -0.09
    离å¼ĢäºĨ
    -0.08
    åĸĦ
    -0.08
    å¿ĥåĬ¨
    -0.08
    æ¢Ĩ
    -0.08
    erce
    -0.08
    æİĬ
    -0.08
    èģĶåIJĪä¼ļ
    -0.08
    POSITIVE LOGITS
    ç³ľ
    0.09
    æĨ¬
    0.09
    uck
    0.09
    fel
    0.09
    æ¦Ĥæĭ¬
    0.08
    æĸĻ
    0.08
    دÙĪ
    0.08
    imest
    0.08
    åij¶
    0.08
    INI
    0.08
    Activations Density 0.048%

    No Known Activations