© 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. 20706
    Prev
    Next
    INDEX
    Explanations

    question or statement start

    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
    etheless
    -0.08
    人æĦı
    -0.07
     (${
    -0.07
    unia
    -0.07
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.07
    è¿ĺèĥ½å¤Ł
    -0.06
    幸è¿IJçļĦæĺ¯
    -0.06
    mals
    -0.06
     everything
    -0.06
     Sands
    -0.06
    POSITIVE LOGITS
    รà¹īà¸Ńย
    0.07
    udev
    0.07
    ington
    0.07
    olon
    0.07
     Garuda
    0.07
    nero
    0.07
    Genres
    0.07
    ipu
    0.07
    _mime
    0.07
    å¹ħ度
    0.07
    Activations Density 0.210%

    No Known Activations