© 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. 35217
    Prev
    Next
    INDEX
    Explanations

    place names and technical terms

    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
     “
    -0.08
     (...)
    -0.07
    为æĬĵæīĭ
    -0.06
    为å¥ijæľº
    -0.06
    为ä¾ĭ
    -0.06
    æī§åĭ¤
    -0.06
    åIJĮåŁİ
    -0.06
     (~
    -0.06
    /
    -0.05
    ï¼ı
    -0.05
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.11
    ĵåIJį
    0.10
    ŀæĢ§
    0.10
    ONEY
    0.10
     اÙĦعرا
    0.10
    CHIP
    0.10
     سبØŃاÙĨ
    0.10
    ngine
    0.10
    alendar
    0.10
    âĺĺ
    0.09
    Activations Density 5.904%

    No Known Activations