© 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. 16465
    Prev
    Next
    INDEX
    Explanations

    back and against

    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
    æł¹æį®ä¸įåIJĮ
    -0.23
    è¾ĥä½İ
    -0.21
    ä½ĵè´¨
    -0.20
    æĽ´ä½İ
    -0.20
    æĪ¾
    -0.20
    åı¦ä¸ĢåįĬ
    -0.19
    åĵ½
    -0.19
    Forge
    -0.18
    (Window
    -0.18
    haps
    -0.18
    POSITIVE LOGITS
    åIJijä¸Ĭ
    0.21
    åĽ¢
    0.20
    entr
    0.18
    ught
    0.18
     lighten
    0.18
    ieved
    0.18
    pin
    0.17
    åĦ¿
    0.17
     bo
    0.17
    gew
    0.17
    Activations Density 0.004%

    No Known Activations