© 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. 27679
    Prev
    Next
    INDEX
    Explanations

    too fast or early

    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
    utc
    -0.09
    å¸ĥ
    -0.09
    bul
    -0.09
    -doc
    -0.08
    ä¼ĺ
    -0.08
    å»¶æľŁ
    -0.08
    /swagger
    -0.08
    åį§
    -0.08
     Tough
    -0.08
    .userAgent
    -0.08
    POSITIVE LOGITS
    太快
    0.19
    æĢ¥äºİ
    0.18
     premature
    0.16
    åĮĨ
    0.14
    æĢ¥å¿Ļ
    0.13
     haste
    0.13
     prematurely
    0.13
     rush
    0.13
     rushing
    0.12
    çĿĢæĢ¥
    0.12
    Activations Density 0.096%

    No Known Activations