© 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. 9839
    Prev
    Next
    INDEX
    Explanations

    broken, spirit, tame

    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
    ruc
    -0.10
     Oswald
    -0.09
    apus
    -0.09
    åIJ¸
    -0.08
    ANC
    -0.08
    ifu
    -0.08
    ovie
    -0.08
    åı¥
    -0.08
    foy
    -0.08
    _State
    -0.08
    POSITIVE LOGITS
    驯
    0.15
    骥
    0.11
     Habit
    0.10
    çľ¼ç¥ŀ
    0.10
    涩
    0.10
    æľī趣çļĦ
    0.10
    çļĦçľ¼ç¥ŀ
    0.10
    æĦıä¹īä¸Ĭ
    0.10
    ãģĹãģĦ
    0.09
    è¿Ļæł·ä¸Ģ个
    0.09
    Activations Density 0.061%

    No Known Activations