© 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. 13152
    Prev
    Next
    INDEX
    Explanations

    Workday Financial Management, BlackBerry 10, Google Glass, GilmanSound

    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
    åĢ¦
    -0.20
     NTN
    -0.19
    åŃļ
    -0.18
    GP
    -0.18
    QQ
    -0.18
    gil
    -0.17
    åIJĦèĩªçļĦ
    -0.17
     pl
    -0.17
    èĻ¢
    -0.17
     yourself
    -0.17
    POSITIVE LOGITS
    çļĦ帮åĬ©ä¸ĭ
    0.25
    æıIJä¾ĽçļĦ
    0.24
    帮å¿Ļ
    0.23
    aida
    0.23
    çļĦ帮åĬ©
    0.22
    ighth
    0.21
    ä¾ĽåĽ¾
    0.21
    æīĢæıIJä¾Ľ
    0.20
    åįıåĬ©
    0.20
    é«ĺåĵģè´¨
    0.19
    Activations Density 0.063%

    No Known Activations