© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    shutdown, strike, cap, lockout

    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
    æľ¬æ¬¡æ´»åĬ¨
    -0.09
    æ¯ı个人çļĦ
    -0.09
    éĥ¨åī¯
    -0.09
    velt
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
     kê
    -0.08
    åģļ强
    -0.08
    ä¸įäºĨ
    -0.08
    arkan
    -0.08
    带头
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.09
    èĥĮæĻ¯ä¸ĭ
    0.08
    好è¯Ħ
    0.08
    ech
    0.08
    Unnamed
    0.08
    éªĦåĤ²
    0.08
    身躯
    0.08
    пл
    0.08
    cir
    0.08
    æĽ´æ·±
    0.08
    Activations Density 0.004%

    No Known Activations