© 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. 42872
    Prev
    Next
    INDEX
    Explanations

    .LoggerFactory

    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
    unti
    -0.07
    isht
    -0.07
    ly
    -0.06
    ¶
    -0.06
    ugas
    -0.06
    éĥİ
    -0.06
    .ex
    -0.06
    ten
    -0.06
    "
    -0.06
     she
    -0.06
    POSITIVE LOGITS
    ä¸įåıĬ
    0.09
    åħ¶æŀĹ
    0.08
    ÏģοÏįν
    0.07
    ÄĽÅ¾
    0.07
    forge
    0.07
    èĬľ
    0.07
    -linux
    0.07
    å·įå·į
    0.07
    лле
    0.07
    alon
    0.07
    Activations Density 0.337%

    No Known Activations