© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41258
    Prev
    Next
    INDEX
    Explanations

    error detecting and correction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    airo
    -0.07
    è°¨æħİ
    -0.07
    ãģĮä»ĺ
    -0.07
     previs
    -0.07
    ä¸įèĥ½åIJĥ
    -0.07
    hoa
    -0.07
    .destroy
    -0.07
    æĭĽçĶŁå·¥ä½ľ
    -0.07
    aro
    -0.06
    åĬ¨å¼¹
    -0.06
    POSITIVE LOGITS
    以å¤ĸçļĦ
    0.08
     unaffected
    0.08
    ä¸į移
    0.08
    fert
    0.08
    没æľīéĹ®é¢ĺ
    0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.08
    åĢĴæĺ¯
    0.08
     cies
    0.07
    æĶ¯æĮģåĬĽåº¦
    0.07
    nth
    0.07
    Activations Density 0.113%

    No Known Activations