© 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. 11189
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    æŁĶ软
    -0.20
    äºĴ
    -0.20
     Kun
    -0.18
    виз
    -0.18
    inherit
    -0.18
    æł¼å°Ķ
    -0.18
     Buck
    -0.18
     Stevens
    -0.18
    çľ¨çľ¼
    -0.18
     Tribute
    -0.18
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.36
    ä¸įäºĨ
    0.34
    æĹłç¼ĺ
    0.23
    éĻ¤å¤ĸ
    0.23
     nor
    0.23
    åıįèĢĮ
    0.22
    常æĢģ
    0.22
    removeAttr
    0.22
    åĿı
    0.21
    æīª
    0.20
    Activations Density 0.385%

    No Known Activations