© 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. 25274
    Prev
    Next
    INDEX
    Explanations

    orientation 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
    usher
    -0.08
    æĵį
    -0.08
    èĮĥçķ´
    -0.08
    ä¸įèĪį
    -0.07
    ancell
    -0.07
     Ñģпла
    -0.07
     délég
    -0.07
     Replacement
    -0.07
     PATH
    -0.07
    _nb
    -0.07
    POSITIVE LOGITS
     orientation
    0.15
    orientation
    0.13
     orientations
    0.13
     Orientation
    0.11
    Orientation
    0.11
    éĿ¢åIJij
    0.11
     flipped
    0.10
    翻转
    0.10
     orient
    0.10
    _orientation
    0.10
    Activations Density 0.077%

    No Known Activations