© 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. 10860
    Prev
    Next
    INDEX
    Explanations

    feeling

    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
    è°ģçŁ¥éģĵ
    -0.19
    imals
    -0.19
    çľĭä¸Ĭåİ»
    -0.19
    辫
    -0.18
    lan
    -0.18
    icode
    -0.17
    appearance
    -0.17
    uddle
    -0.17
    å±ķ示äºĨ
    -0.17
    桧
    -0.17
    POSITIVE LOGITS
    æĿ¥èĩª
    0.21
    äºĨä¸Ģä¸ĭ
    0.21
    t
    0.20
    ãĤĴæĦŁãģĺ
    0.20
    ä¾Ĩèĩª
    0.19
    ä¸ĢèĤ¡
    0.19
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.19
    ãĥ¼ãĥ³
    0.19
    æµĵæµĵçļĦ
    0.19
    å°±çŁ¥éģĵ
    0.18
    Activations Density 0.019%

    No Known Activations