© 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. 15742
    Prev
    Next
    INDEX
    Explanations

    Reliable Source

    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
    åIJĮæŶå°Ĩ
    -0.07
    ä¸įåıĹ
    -0.07
    ä¸į离
    -0.07
    aum
    -0.07
    约车
    -0.07
    UND
    -0.06
    ãģ£ãģĵãģĨ
    -0.06
    othe
    -0.06
    çIJĨ论ä¸İ
    -0.06
    æ²¹çĽIJ
    -0.06
    POSITIVE LOGITS
    htm
    0.07
    _kernel
    0.07
     Erw
    0.07
    ARRIER
    0.06
    æĸ¯åħĭ
    0.06
    ç¹½
    0.06
     comprov
    0.06
    Ùİاع
    0.06
    _skb
    0.06
    æīįçŁ¥éģĵ
    0.06
    Activations Density 0.045%

    No Known Activations