© 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. 6809
    Prev
    Next
    INDEX
    Explanations

    arts, activities, music, poetry

    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
    éĩijåĪļ
    -0.10
     Tier
    -0.10
    è§īæĤŁ
    -0.09
    åĿļåĽº
    -0.09
    å±ħ
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    åĢŁéī´
    -0.08
    åIJĥäºı
    -0.08
    æĿĥå¨ģ
    -0.08
    éĿŀæ³ķ
    -0.08
    POSITIVE LOGITS
    çī¹éķ¿
    0.17
    èīºæľ¯
    0.13
    æĸĩèīº
    0.12
    ä¹IJåĻ¨
    0.12
    çIJ´
    0.12
    åĻ¨æĿIJ
    0.11
    arts
    0.11
    éĴ¢çIJ´
    0.11
    æĸĩåĮĸèīºæľ¯
    0.11
    ðŁİ¨
    0.11
    Activations Density 0.069%

    No Known Activations