© 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. 10939
    Prev
    Next
    INDEX
    Explanations

    office or Service location

    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
     mine
    -0.18
     gent
    -0.18
     lur
    -0.17
    ä»Ķ
    -0.17
    èĽ©
    -0.17
    ç¡ķ
    -0.17
    糸
    -0.17
    竦
    -0.17
    æĦŁåĬ¨
    -0.17
    å¾®åķĨ
    -0.17
    POSITIVE LOGITS
    åĪĹ
    0.22
    ãģĬäºĴ
    0.21
    ä¸ĩä¸Ģ
    0.21
    泡泡
    0.21
    ç´¢åıĸ
    0.20
    æĪĸå°Ĩ
    0.20
    ä¸įå®ļ
    0.20
    为åĩĨ
    0.20
    åĬĽè¿ĺæĺ¯
    0.19
    ãĥ¡ãĥ¼ãĤ
    0.19
    Activations Density 0.019%

    No Known Activations