© 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. 20813
    Prev
    Next
    INDEX
    Explanations

    diagonal, triangular, acyclic graphical

    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
    继ç»Ń沿
    -0.09
    vos
    -0.09
    tingham
    -0.09
    ä¸įæģ¯
    -0.09
    马éĩĮ
    -0.08
     Continua
    -0.08
    stek
    -0.08
    baugh
    -0.08
    arena
    -0.08
    å¨Ĩ
    -0.08
    POSITIVE LOGITS
    ness
    0.07
    ment
    0.07
    ed
    0.07
    ä¸Ķ
    0.07
    izable
    0.06
    åĨĻçĿĢ
    0.06
    _sparse
    0.06
    reflect
    0.06
    -ish
    0.06
    èĸ°
    0.06
    Activations Density 0.002%

    No Known Activations