© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    for better or worse, coast to coast

    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
     ÐIJлекÑģан
    -0.22
    ä½łä¸į
    -0.20
    éŀĺ
    -0.20
    æ»ļæ»ļ
    -0.20
    åĬ©
    -0.19
    edu
    -0.19
    etc
    -0.19
    è¿ĩæĿ¥
    -0.19
     подÑĢобн
    -0.19
    lya
    -0.18
    POSITIVE LOGITS
     and
    0.26
     и
    0.21
     &
    0.21
    åĴĮ
    0.19
     Lo
    0.19
    andon
    0.19
    .getSession
    0.18
    xef
    0.18
    -
    0.18
    èļĿ
    0.18
    Activations Density 0.062%

    No Known Activations