© 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. 16623
    Prev
    Next
    INDEX
    Explanations

    LaTeX tikz graphs

    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
    çĽ
    -0.07
    ilon
    -0.07
    ystem
    -0.07
    zcz
    -0.07
     liable
    -0.06
    ype
    -0.06
    ashed
    -0.06
     ilmu
    -0.06
    usso
    -0.06
    agnet
    -0.06
    POSITIVE LOGITS
    èĩªåĬ¨åĮĸ
    0.08
    érica
    0.07
    æĸŃ
    0.07
    multiline
    0.07
     Raz
    0.07
    weiler
    0.07
    å¾Ĺ天
    0.07
    _DAC
    0.07
    uche
    0.07
    mk
    0.07
    Activations Density 0.001%

    No Known Activations