© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    æĥļ
    -0.22
    å¿¿
    -0.20
    deg
    -0.19
    /LICENSE
    -0.19
    keh
    -0.18
    |min
    -0.18
     Wend
    -0.18
    uen
    -0.18
    .eth
    -0.18
    æĮ«
    -0.18
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.28
    è¿Ļéĥ¨åĪĨ
    0.25
    åįķçĭ¬
    0.22
    é³Ħ
    0.22
     zost
    0.21
    åı¦è¡Į
    0.21
    åĨįåĬłä¸Ĭ
    0.20
    鸳
    0.20
    åı¦
    0.20
    å¥
    0.20
    Activations Density 0.048%

    No Known Activations