© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    time delay lag shift

    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
    票
    -0.11
    æ¸ħæī«
    -0.10
    ç»Ī身
    -0.09
    趣
    -0.09
    å°±æѤ
    -0.09
    ç½®æį¢
    -0.09
    å¯Łçľĭ
    -0.09
    SMART
    -0.09
    ãĤ¹ãĥŀ
    -0.09
    ä¸įä¸ĭ
    -0.09
    POSITIVE LOGITS
    æ»ŀåIJİ
    0.29
     lag
    0.25
    å»¶è¿Ł
    0.24
    lag
    0.23
    delay
    0.21
     delay
    0.21
    è¿Ł
    0.20
    延误
    0.19
     Delay
    0.18
     Lag
    0.18
    Activations Density 0.122%

    No Known Activations