© 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. 47536
    Prev
    Next
    INDEX
    Explanations

    color: CSS property

    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
    áv
    -0.07
    qml
    -0.07
    åıĬ个人
    -0.07
    ricks
    -0.07
    .pet
    -0.07
    _UNDER
    -0.07
     اÙĦعص
    -0.07
    WXYZ
    -0.07
    æĸ°éĶIJ
    -0.07
    λι
    -0.07
    POSITIVE LOGITS
     mạ
    0.07
    ï¸İ
    0.07
     Gunn
    0.06
    幸ç¦ıçļĦ
    0.06
     invi
    0.06
    zman
    0.06
    niv
    0.06
    zana
    0.06
    adic
    0.06
    íķŃ
    0.06
    Activations Density 0.003%

    No Known Activations