© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37422
    Prev
    Next
    INDEX
    Explanations

    recognize / recognition

    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
    å¹´ä¹ĭ
    -0.09
    çİĭåºľ
    -0.08
    æĶ¹è¿Ľ
    -0.08
    æīĴ
    -0.08
    uese
    -0.08
    pData
    -0.08
    审议
    -0.08
    ç½®
    -0.08
    读åIJİ
    -0.08
    æıIJ示
    -0.08
    POSITIVE LOGITS
    æī¿è®¤
    0.19
    认åı¯
    0.16
    çļĦ认åı¯
    0.13
    认
    0.13
    èªįãĤģ
    0.11
     ìĿ¸ìłķ
    0.11
    èªį
    0.11
    Acknowled
    0.11
    认åIJĮ
    0.11
    ack
    0.10
    Activations Density 0.033%

    No Known Activations