© 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. 15843
    Prev
    Next
    INDEX
    Explanations

    Key-value pairs

    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
    ilia
    -0.19
    erk
    -0.19
    ViewItem
    -0.19
    legate
    -0.17
    squ
    -0.17
    ego
    -0.17
    åŃĺåľ¨
    -0.17
     RedirectTo
    -0.17
    appendTo
    -0.17
    æĬĢæľ¯åĴĮ
    -0.16
    POSITIVE LOGITS
    _ta
    0.21
    çİĭåºľ
    0.20
    åıijå±ķ空éĹ´
    0.19
    æīĭèĦļ
    0.18
    åĮª
    0.18
    ä¸ĩåįĥ
    0.18
    thouse
    0.17
    åįİ润
    0.17
    对éĿ¢
    0.17
    -divider
    0.17
    Activations Density 0.419%

    No Known Activations