© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    relative path components

    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
    -0.07
    æľ¬å°ı说
    -0.07
    erable
    -0.06
    ÙĬÙĪÙĨ
    -0.06
    loses
    -0.06
    æĨ¬
    -0.06
    ç±»çļĦ
    -0.06
    åı¥è¯Ŀ说
    -0.06
    åıĮé±¼
    -0.06
    /inet
    -0.06
    POSITIVE LOGITS
    hin
    0.09
    thers
    0.08
    åĭĩå¾Ģ缴åīį
    0.07
    antul
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    OUNDS
    0.07
    ismus
    0.07
    rome
    0.07
    æĮģä¹ĭ以
    0.07
    README
    0.07
    Activations Density 0.028%

    No Known Activations