© 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. 25713
    Prev
    Next
    INDEX
    Explanations

    MCD Application Team

    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
    anford
    -0.07
    ×IJ×Ķ
    -0.07
    å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.07
    ifax
    -0.07
    isco
    -0.07
    raid
    -0.07
    utom
    -0.07
     Terd
    -0.07
    æĸŃäºĨ
    -0.07
    corp
    -0.07
    POSITIVE LOGITS
    æŀģ
    0.07
     Manson
    0.06
     Gam
    0.06
    è¯ł
    0.06
    estyle
    0.06
     doub
    0.06
    .Json
    0.06
    (Rect
    0.06
    çĭĤ
    0.06
    ÙĪائ
    0.06
    Activations Density 0.023%

    No Known Activations