© 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. 62413
    Prev
    Next
    INDEX
    Explanations

    percentages and coordinates

    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
    ecat
    -0.07
    iliano
    -0.07
    è§ģ人
    -0.07
    Selectable
    -0.07
    angkan
    -0.07
     Lass
    -0.07
    ÏĦεÏį
    -0.07
    orado
    -0.07
    pressed
    -0.07
     lá
    -0.07
    POSITIVE LOGITS
    utin
    0.07
    atrix
    0.07
    -span
    0.07
     slik
    0.07
    avelength
    0.07
    _locator
    0.07
    éĽĨä¸Ń度
    0.07
    adius
    0.07
     unfavor
    0.07
    LOC
    0.07
    Activations Density 0.004%

    No Known Activations