© 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. 61615
    Prev
    Next
    INDEX
    Explanations

    planning, tasks, and organization

    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
    _tar
    -0.09
    使çĶ¨çļĦ
    -0.09
    drawing
    -0.09
    addTo
    -0.09
    禺
    -0.09
    æ¤Ĵ
    -0.08
    ç¨ļ
    -0.08
    akistan
    -0.08
    ogy
    -0.08
    AKER
    -0.08
    POSITIVE LOGITS
    æĶ¾æīĭ
    0.10
    åIJĦ个çݯèĬĤ
    0.09
    æĪIJ为ä¸Ģ个
    0.09
    å¯ĨéĽĨ
    0.09
    ç´§åĩij
    0.09
    çħĬ
    0.09
    åľ°åĿª
    0.09
    STS
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
    åIJĦæĸ¹éĿ¢
    0.08
    Activations Density 0.054%

    No Known Activations