© 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. 31801
    Prev
    Next
    INDEX
    Explanations

    every year, week, time

    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
    æ°¸ä¸į
    -0.11
    ä¸įè´Ł
    -0.09
     pragma
    -0.09
    ETS
    -0.09
    ummies
    -0.08
    为ä»Ģä¹Īä¸į
    -0.08
    æĥħæĢĢ
    -0.08
    é¦
    -0.08
    夺
    -0.08
    主è¦ģæľī
    -0.08
    POSITIVE LOGITS
    æ¯ı个
    0.11
    æ¯ıä¸Ģ
    0.11
    çļĦ人éĥ½
    0.11
    人éĥ½
    0.10
    æ¯ı次
    0.10
     маÑģÑĤ
    0.10
    ANNER
    0.10
    æ¶īåıĬåĪ°
    0.10
    beg
    0.09
    æĪij们éĥ½
    0.09
    Activations Density 0.029%

    No Known Activations