© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20338
    Prev
    Next
    INDEX
    Explanations

    component and direction

    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
    anford
    -0.09
    å·¥åĨľ
    -0.08
    åıij泡
    -0.07
    baum
    -0.07
    æ¹ĥ
    -0.07
    ibold
    -0.07
    æľīåħ³äºĭ项
    -0.07
    声ä¸Ń
    -0.07
    èį«
    -0.07
    \models
    -0.06
    POSITIVE LOGITS
    åĪĨéĩı
    0.13
     components
    0.12
     Components
    0.11
     component
    0.11
    components
    0.10
    component
    0.10
    Components
    0.10
     Component
    0.10
     componentes
    0.10
     componente
    0.10
    Activations Density 0.004%

    No Known Activations