© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7586
    Prev
    Next
    INDEX
    Explanations

    typographical errors and misunderstandings

    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
    çªģåĩºéĹ®é¢ĺ
    -0.10
    åĬ£
    -0.10
    满æĦı度
    -0.09
    ä¹ĭåĬ¿
    -0.09
    满æĦı
    -0.09
     chÃło
    -0.09
    å¼Ģæ°´
    -0.09
    ç¥Ĭ
    -0.09
    èѦåijĬ
    -0.09
    entai
    -0.09
    POSITIVE LOGITS
    误ä¼ļ
    0.21
    误解
    0.18
    误
    0.18
    éĶĻäºĨ
    0.18
     mistake
    0.18
    éĶĻ
    0.17
    失误
    0.17
    誤
    0.15
     mistaken
    0.15
    éĶĻ误
    0.15
    Activations Density 0.100%

    No Known Activations