© 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. 17807
    Prev
    Next
    INDEX
    Explanations

    direction and angles

    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
    Ïģιθ
    -0.07
    å½¢å¼ıçļĦ
    -0.07
    àªŃ
    -0.07
    alna
    -0.07
    WindowSize
    -0.07
     disag
    -0.07
    éĻIJé¢Ŀ
    -0.07
    笳
    -0.07
    å½¢å¼ı
    -0.07
    åĪĿæľŁçļĦ
    -0.07
    POSITIVE LOGITS
     orientation
    0.09
     orientations
    0.09
    çļĦè§Ĵ度
    0.08
     оÑĢи
    0.08
     direction
    0.08
     angles
    0.08
     angle
    0.08
     alignment
    0.08
     orient
    0.08
    -align
    0.08
    Activations Density 0.001%

    No Known Activations