© 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. 13691
    Prev
    Next
    INDEX
    Explanations

    enumeration

    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
    APON
    -0.20
     BANK
    -0.18
    INA
    -0.17
    unt
    -0.17
    é¾Ī
    -0.17
    客æĪ·æıIJä¾Ľ
    -0.17
     кли
    -0.17
    UNT
    -0.17
     currencies
    -0.17
    ina
    -0.17
    POSITIVE LOGITS
    两èĢħ
    0.32
    äºĮèĢħ
    0.28
    è¿Ļ两个
    0.27
    è¿Ļ两
    0.26
    ä¸īæĺ¯
    0.25
    两项
    0.24
    æĸĻ
    0.23
    è¿Ļ两ç§į
    0.22
    ä¸¤å¼ł
    0.19
    第ä¸ī个
    0.19
    Activations Density 0.687%

    No Known Activations