© 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. 41765
    Prev
    Next
    INDEX
    Explanations

    path drawing commands

    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
    boxed
    -0.07
    å°ĺ
    -0.06
    èĬ¸
    -0.06
     sealed
    -0.06
    æ°´åľŁ
    -0.06
    ush
    -0.06
     Narrow
    -0.06
    æİĴéĺŁ
    -0.06
     Watch
    -0.06
     Feld
    -0.06
    POSITIVE LOGITS
    roke
    0.08
    å©Ģ
    0.08
    hil
    0.08
    gada
    0.08
    polygon
    0.08
     moveTo
    0.08
    ATERIAL
    0.08
    .stroke
    0.08
    .moveTo
    0.08
    åĽĽæĿ¡
    0.08
    Activations Density 0.063%

    No Known Activations