© 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. 27141
    Prev
    Next
    INDEX
    Explanations

    Jeremy followed by names

    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
    otch
    -0.10
    å¤§éĽ¨
    -0.10
    inky
    -0.09
    ively
    -0.09
    itional
    -0.09
    пÑĢом
    -0.09
    رز
    -0.09
    æĸ°åŁİ
    -0.09
    ieren
    -0.09
    urb
    -0.09
    POSITIVE LOGITS
    aceous
    0.11
    ../../../
    0.10
    æѤå¤ĸ
    0.10
     же
    0.09
    stration
    0.09
    ãģ£ãģ¨
    0.09
    =-=-=-=-
    0.09
     rÃłng
    0.09
    asure
    0.09
    缶
    0.08
    Activations Density 0.029%

    No Known Activations