© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14675
    Prev
    Next
    INDEX
    Explanations

    enter variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    带头人
    -0.19
    å±±ä¸Ĭ
    -0.17
    ohl
    -0.16
    éķ¿çŁŃ
    -0.16
    ombo
    -0.16
    è¯Ŀ说
    -0.15
    æĿ¥èĩª
    -0.15
    åĻ¨åħ·
    -0.15
    æ¸ļ
    -0.15
     bergen
    -0.15
    POSITIVE LOGITS
    prising
    0.41
    prises
    0.32
    prise
    0.25
    CriticalSection
    0.24
     adulthood
    0.21
    /out
    0.19
    è¿ĽæĿ¥
    0.19
    è¿Ľåİ»
    0.19
    /disable
    0.19
    prisingly
    0.18
    Activations Density 0.056%

    No Known Activations