© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    winding ends or three-legged

    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
     contextual
    -0.08
    سر
    -0.08
    æĿĥè¡¡
    -0.07
     Bullet
    -0.07
    åģļäºĭæĥħ
    -0.07
    leman
    -0.07
     süreç
    -0.07
     Atomic
    -0.07
    Bullet
    -0.06
    åĬłéĢŁåĻ¨
    -0.06
    POSITIVE LOGITS
    .rotate
    0.08
     rotates
    0.08
    åľ¨ä¸ī
    0.08
    selectedIndex
    0.08
     Tiong
    0.07
    ATTERN
    0.07
     напÑĢÑıжение
    0.07
     rotating
    0.07
    ypsy
    0.07
    REFERRED
    0.07
    Activations Density 0.002%

    No Known Activations