© 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. 9859
    Prev
    Next
    INDEX
    Explanations

    FILED documents

    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
    lund
    -0.09
    rie
    -0.09
    ness
    -0.08
    é¢ĩ
    -0.08
    eller
    -0.08
    dater
    -0.08
    ly
    -0.08
    æĿ¥ä¸´
    -0.08
    ám
    -0.08
    di
    -0.08
    POSITIVE LOGITS
    åŁĴ
    0.11
    箧
    0.10
    ÑİÑī
    0.10
    _managed
    0.10
    สะสม
    0.10
    ëŁ¿
    0.10
    usi
    0.10
    æľī两个
    0.09
    unte
    0.09
    ละ
    0.09
    Activations Density 0.052%

    No Known Activations