© 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. 11566
    Prev
    Next
    INDEX
    Explanations

    `Q:` and `Frank Hall`

    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
    íĹĢ
    -0.23
     поÑģколÑĮ
    -0.22
    ÑĩÑĢежден
    -0.20
    icc
    -0.20
    axed
    -0.20
    åľ¨åIJĮä¸Ģ
    -0.19
    è¿ĩæĿ¥
    -0.19
    ropa
    -0.19
     кнопк
    -0.19
    .dds
    -0.18
    POSITIVE LOGITS
    éĢĤéĩı
    0.29
    çĥŃéĩı
    0.23
    åĪĨæł¡
    0.23
    æ¸ħæ·¡
    0.22
    èIJ¥åħ»ä»·åĢ¼
    0.22
    éű
    0.21
    èĨ³é£Ł
    0.21
    å¦Ĥæľīä¾µæĿĥ
    0.21
    æĸĩåĮĸä¼łåªĴ
    0.21
    åĮĹ京åĨ¬å¥¥
    0.20
    Activations Density 0.002%

    No Known Activations