© 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. 49888
    Prev
    Next
    INDEX
    Explanations

    code structures and numbers

    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
    nitz
    -0.07
    äºī
    -0.07
    nostÃŃ
    -0.07
    ãĤ¤ãĤº
    -0.06
    满å¿ĥ
    -0.06
     RemoteException
    -0.06
    Ñĥй
    -0.06
    esan
    -0.06
    versa
    -0.06
    ç«ŀ
    -0.06
    POSITIVE LOGITS
    ibaldi
    0.08
    èİİ
    0.08
    ledo
    0.07
    ushman
    0.07
     tw
    0.07
     FRANC
    0.07
    itty
    0.07
    iby
    0.07
    .ToInt
    0.07
    ismet
    0.06
    Activations Density 0.377%

    No Known Activations