© 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. 16210
    Prev
    Next
    INDEX
    Explanations

    directions (north, south, east, west)

    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
    ì·¨
    -0.08
    /il
    -0.07
    mant
    -0.07
    ubat
    -0.07
    ä¸įæĢĿ
    -0.07
    hoot
    -0.07
    bris
    -0.07
    ä¸Ģæī¶
    -0.07
    rieg
    -0.07
     magnÃŃ
    -0.07
    POSITIVE LOGITS
    横åIJij
    0.11
     horizontal
    0.11
     horizontally
    0.11
     clockwise
    0.11
     toward
    0.11
    顺æŶéĴĪ
    0.11
     towards
    0.10
    åIJijåı³
    0.10
     vertically
    0.10
    à¸Ĺิศ
    0.10
    Activations Density 0.207%

    No Known Activations