© 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. 62540
    Prev
    Next
    INDEX
    Explanations

    detector, sensor, panel, laser, array

    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
    agar
    -0.09
    å°±è¿Ļæł·
    -0.09
    ä¹ĭéģĵ
    -0.08
     intim
    -0.08
    è¿ģ
    -0.08
    é¾Ħ
    -0.08
    ath
    -0.08
    /tools
    -0.08
    éĺª
    -0.08
    ç»ıåİĨ
    -0.08
    POSITIVE LOGITS
    为主çļĦ
    0.12
    å¼ıçļĦ
    0.12
    å¼ı
    0.11
    -based
    0.11
    为主
    0.10
    ä¸ºæł¸å¿ĥçļĦ
    0.09
    itori
    0.09
     technology
    0.09
    æĬĢæľ¯
    0.09
    issan
    0.09
    Activations Density 0.286%

    No Known Activations