© 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. 49390
    Prev
    Next
    INDEX
    Explanations

    cloud computing services and platforms

    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
    åĿĬ
    -0.11
    ven
    -0.09
    phy
    -0.09
    åĵĦ
    -0.09
     полов
    -0.09
    naire
    -0.09
    央è§Ĩ
    -0.08
    .DependencyInjection
    -0.08
    æ³ķå®Ŀ
    -0.08
    apore
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľèĢħ
    0.11
    inary
    0.11
    workers
    0.09
    åĮĸçļĦ
    0.09
    éĻĽ
    0.09
    0.09
    quake
    0.09
    éĻ¤æѤ
    0.08
    åIJįåı«
    0.08
    纪
    0.08
    Activations Density 0.031%

    No Known Activations