© 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. 53869
    Prev
    Next
    INDEX
    Explanations

    help others

    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
    éĽĴ
    -0.10
    åĩłä¹İæīĢæľī
    -0.10
    人为
    -0.10
    æĮª
    -0.09
    åĩłä¹İ
    -0.09
    åºĨç¥Ŀ
    -0.09
    å³Ļ
    -0.09
    èĻ¹æ¡¥
    -0.08
    eus
    -0.08
    çĻ½é¢Ĩ
    -0.08
    POSITIVE LOGITS
    è·ŁæĪij
    0.11
    ä»ĬåIJİ
    0.09
    æĹ¥åIJİ
    0.09
    ä¸įè¦ģåĨį
    0.09
    æľªæĿ¥
    0.09
     similar
    0.09
    åIJİæĿ¥
    0.09
     someday
    0.08
    ä¸ĩä¸Ģ
    0.08
    ä¸İæѤ
    0.08
    Activations Density 0.057%

    No Known Activations