© 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. 4865
    Prev
    Next
    INDEX
    Explanations

    for

    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
    æĹģè¾¹çļĦ
    -0.11
    åıĪæľī
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    лин
    -0.09
    è¯Ķ
    -0.08
    ä¸ĸçķĮçļĦ
    -0.08
    身边çļĦ
    -0.08
    ãģ¨ãĤĤ
    -0.08
    ãģĹãģ¦ãģĬãģı
    -0.08
    _dt
    -0.08
    POSITIVE LOGITS
    instead
    0.10
     instead
    0.10
    æĿ¥åģļ
    0.10
     вмеÑģÑĤ
    0.10
    èĢĮéĿŀ
    0.09
    ä¹°ä¸ľè¥¿
    0.09
    ä»£æĽ¿
    0.09
    æĿ¥
    0.09
     shoe
    0.09
     supreme
    0.09
    Activations Density 0.318%

    No Known Activations