© 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. 13363
    Prev
    Next
    INDEX
    Explanations

    Colleges and places

    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
    髦
    -0.19
    (register
    -0.18
    Democrats
    -0.18
     anom
    -0.18
     Ved
    -0.18
     disob
    -0.18
    ä¸Ģç«Ļ
    -0.18
    unn
    -0.17
    èĪħ
    -0.17
    é¢Ĩ导èĢħ
    -0.17
    POSITIVE LOGITS
    对æīĭ
    0.23
     counterpart
    0.23
     counterparts
    0.23
    åIJĮæł·æĺ¯
    0.21
    ç«ŀäºī对æīĭ
    0.21
     Prel
    0.20
    xor
    0.19
    享æľī
    0.18
    åĽ´
    0.18
    Ñīи
    0.18
    Activations Density 0.122%

    No Known Activations