© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9122
    Prev
    Next
    INDEX
    Explanations

    only

    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
     Ign
    -0.08
    ä¸įåı¯èĥ½
    -0.08
     Fro
    -0.08
    ç»Ŀ对ä¸įä¼ļ
    -0.08
    nex
    -0.08
    athed
    -0.08
    æ»
    -0.08
    æľ«
    -0.08
    æ¼ł
    -0.08
    ä¸Ģäºĭ
    -0.08
    POSITIVE LOGITS
    ä¾ĿéĿł
    0.12
    ä¸ŃåİŁ
    0.10
    æĸ½
    0.10
    ä»ħæľī
    0.10
    éĿ¢åīį
    0.10
    .CopyTo
    0.10
    ç²¹
    0.09
    æľĢåŁºæľ¬çļĦ
    0.09
    æłĩæĺİ
    0.09
    è°İè¨Ģ
    0.09
    Activations Density 0.077%

    No Known Activations