© 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. 30950
    Prev
    Next
    INDEX
    Explanations

    direction and orientation

    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
    æĢ»ä»·
    -0.06
    æ±ŀ
    -0.06
    黯
    -0.06
    çĴĢ
    -0.06
     اجر
    -0.06
    è¿Ń代
    -0.06
    Overflow
    -0.06
    ?id
    -0.06
    (identifier
    -0.06
    è¡Ķ
    -0.06
    POSITIVE LOGITS
     directional
    0.15
    -direction
    0.15
    Direction
    0.15
     Direction
    0.14
    çļĦæĸ¹åIJij
    0.14
     orientations
    0.14
    åıĸåIJij
    0.14
     orientation
    0.13
     direction
    0.13
     Orientation
    0.13
    Activations Density 0.102%

    No Known Activations