© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51413
    Prev
    Next
    INDEX
    Explanations

    fighting, panic, Zori, WatchKit

    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
    ä¾ĥ
    -0.09
    æ¶ī
    -0.09
    åĽĬ
    -0.09
    èĩ»
    -0.08
    cel
    -0.08
    åĵī
    -0.08
    è¿ĻäºĽå¹´
    -0.08
    ãģĤãģ®
    -0.08
    沧æ¡ij
    -0.08
    éķ¿æľŁä»¥æĿ¥
    -0.08
    POSITIVE LOGITS
    ä¸Ģ声
    0.10
    enario
    0.10
    ofday
    0.10
    åī§æĥħ
    0.10
    主人åħ¬
    0.10
     дейÑģÑĤвиÑı
    0.09
    俵
    0.09
    æĥħèĬĤ
    0.09
    æķħäºĭ
    0.09
    æĥħæĻ¯
    0.09
    Activations Density 0.011%

    No Known Activations