© 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. 9579
    Prev
    Next
    INDEX
    Explanations

    Gerber, recurrence relations, names ending in berg

    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
    å²±
    -0.08
     teatr
    -0.07
    ollywood
    -0.07
    -ignore
    -0.07
     Arena
    -0.07
    ibble
    -0.07
    _toggle
    -0.07
    weet
    -0.06
    驾驶
    -0.06
    诧
    -0.06
    POSITIVE LOGITS
    emn
    0.08
    å°ijå¹´åĦ¿ç«¥
    0.08
    幼年
    0.07
    -Series
    0.07
    /Runtime
    0.07
    ador
    0.07
    .arm
    0.07
    æĻ¤
    0.07
    arme
    0.07
     semiclass
    0.07
    Activations Density 0.002%

    No Known Activations