© 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. 36945
    Prev
    Next
    INDEX
    Explanations

    large and small

    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
    人家
    -0.10
    ç¬ı
    -0.09
    Rnd
    -0.09
    ambi
    -0.09
    rei
    -0.09
    agram
    -0.08
    æ°´ä¸Ń
    -0.08
    åħ³æ³¨åº¦
    -0.08
    æĹ¥æĬ¥è®°èĢħ
    -0.08
    ç²¾åĬĽ
    -0.08
    POSITIVE LOGITS
    åĨħå¤ĸ
    0.13
    ä¸į论
    0.09
    大å°ı
    0.09
    å¾Īå°ı
    0.09
     small
    0.09
    past
    0.09
    ç®Ĺ
    0.09
    stin
    0.09
    æijĬ
    0.09
    ä¸įåĪĨ
    0.08
    Activations Density 0.078%

    No Known Activations