© 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. 55944
    Prev
    Next
    INDEX
    Explanations

    how do I

    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
    ipur
    -0.07
    /IP
    -0.07
    æĽ¾å¤ļ次
    -0.07
    isper
    -0.07
    ä¹ŁæĽ¾
    -0.07
    erden
    -0.06
    ij¸
    -0.06
    ä»»ä½ł
    -0.06
    @js
    -0.06
     resp
    -0.06
    POSITIVE LOGITS
    estad
    0.08
    ething
    0.08
    æĮĿ
    0.08
    ultipart
    0.07
    æĨ§
    0.07
    achim
    0.07
    æŀ¢
    0.07
    éĩįéĩį
    0.07
    _LAT
    0.07
    astia
    0.07
    Activations Density 0.639%

    No Known Activations