© 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. 38663
    Prev
    Next
    INDEX
    Explanations

    . followed by sentence 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
     `,
    -0.07
    ziger
    -0.07
     {_
    -0.07
    gles
    -0.07
    DESCRIPTION
    -0.07
    CLAIM
    -0.07
    èĩ³æŀģ
    -0.07
    åľ¨çľĭåĪ°
    -0.07
    å§ĭèĩ³
    -0.07
    oref
    -0.07
    POSITIVE LOGITS
    .jpg
    0.13
    .JPG
    0.12
    .png
    0.11
    示æĦıåĽ¾
    0.10
    示æĦı
    0.10
    .PNG
    0.09
     pictured
    0.09
     screenshot
    0.09
     illustration
    0.09
    æĪªåĽ¾
    0.09
    Activations Density 0.824%

    No Known Activations