© 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. 60132
    Prev
    Next
    INDEX
    Explanations

    Âł characters

    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
    åĪ°
    -0.07
    ly
    -0.07
    åľ¨
    -0.07
     ,
    -0.07
    åŃIJ
    -0.07
    ULLET
    -0.07
    1
    -0.06
    -0.06
    ìĿ´
    -0.06
    mith
    -0.06
    POSITIVE LOGITS
    &R
    0.10
    åħ¼æĢ»ç»ıçIJĨ
    0.08
    erbe
    0.08
    ahoma
    0.08
    OMIC
    0.08
    /ay
    0.08
    esima
    0.08
    anisme
    0.08
    swagger
    0.07
    åģ¥åº·ç½ij
    0.07
    Activations Density 0.003%

    No Known Activations