© 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. 64928
    Prev
    Next
    INDEX
    Explanations

    all of our/their/these/this

    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
    ¢
    -0.08
    ized
    -0.08
    IZZ
    -0.07
    off
    -0.07
    èĭ¥å¹²
    -0.07
    æľīæĹł
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
    4
    -0.06
    ase
    -0.06
    5
    -0.06
    POSITIVE LOGITS
    inous
    0.08
    ãģŀ
    0.08
     Äijặn
    0.08
    erno
    0.08
    rames
    0.07
    jÅ¡ÃŃm
    0.07
    /all
    0.07
    odata
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    /she
    0.07
    Activations Density 0.178%

    No Known Activations