© 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. 38050
    Prev
    Next
    INDEX
    Explanations

    version.endswith

    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
    fel
    -0.07
    iras
    -0.06
    asper
    -0.06
     flood
    -0.06
    ice
    -0.06
     fels
    -0.06
     Dor
    -0.06
    atan
    -0.06
    Modal
    -0.06
    æĥ³äºĨ解
    -0.06
    POSITIVE LOGITS
    subtract
    0.08
    OMB
    0.07
    bezieh
    0.07
    Ä«b
    0.07
    averse
    0.07
    omentum
    0.07
    اص
    0.07
    glm
    0.07
    oppers
    0.07
    implicit
    0.07
    Activations Density 0.047%

    No Known Activations