© 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. 8822
    Prev
    Next
    INDEX
    Explanations

    legal cases and articles about America

    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
    _AMD
    -0.07
    æı©
    -0.06
    yal
    -0.06
    çĶ·ç¥ŀ
    -0.06
    åĮķ
    -0.06
    æĿĪ
    -0.06
    ãģ£ãģĵ
    -0.06
    æĺķ
    -0.06
    èŀįèŀį
    -0.06
    ä¼ĺçĶŁ
    -0.06
    POSITIVE LOGITS
     locator
    0.07
    ستر
    0.07
    ocator
    0.07
    relude
    0.07
    gregator
    0.07
    ä¸Ģ空
    0.07
     Peaks
    0.07
    ิà¸ļ
    0.07
    å¹´æľŁ
    0.07
    DX
    0.07
    Activations Density 0.026%

    No Known Activations