© 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. 11220
    Prev
    Next
    INDEX
    Explanations

    colors: red, green, blue, yellow, pink, orange

    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
    ers
    -0.07
     canv
    -0.07
    禽
    -0.07
    apid
    -0.07
    åĬ¡
    -0.06
    Į¨
    -0.06
    奢ä¾Ī
    -0.06
    ough
    -0.06
    omers
    -0.06
     ÙĨÙħا
    -0.06
    POSITIVE LOGITS
    èī²çļĦ
    0.09
    ìĥī
    0.09
    -red
    0.08
    /blue
    0.08
     nhạt
    0.08
    -blue
    0.08
    -orange
    0.08
    -green
    0.08
    -grey
    0.08
    avy
    0.08
    Activations Density 0.061%

    No Known Activations