© 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. 20055
    Prev
    Next
    INDEX
    Explanations

    g, ago, gorge, org

    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
    两æīĭ
    -0.09
    尾巴
    -0.08
    çļĦæĢģ度
    -0.08
    ramid
    -0.08
    anto
    -0.08
    çĦIJ
    -0.08
    åѦç§ij
    -0.08
    æĹ¥æĻļ
    -0.08
    ä¸Ģ个æĸ°çļĦ
    -0.08
    chant
    -0.07
    POSITIVE LOGITS
    ingly
    0.13
    趸
    0.12
     gag
    0.11
    IVA
    0.10
    æľ¬èĥ½
    0.10
    fully
    0.10
    æ½ŀ
    0.08
    æ¿Ĥ
    0.08
    éĶı
    0.08
    /window
    0.08
    Activations Density 0.006%

    No Known Activations