© 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. 63236
    Prev
    Next
    INDEX
    Explanations

    years, decades, career, results, diagnosis

    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
     etc
    -0.07
    gett
    -0.07
    íĮĮ
    -0.07
    ipes
    -0.07
    avo
    -0.06
    io
    -0.06
    etc
    -0.06
    ja
    -0.06
    _aux
    -0.06
    æĹłæŀģ
    -0.06
    POSITIVE LOGITS
    dings
    0.07
    è°¨éĺ²
    0.07
    ÏĢον
    0.07
     olup
    0.07
    asca
    0.07
    еÑĢÑĮ
    0.07
    ë¦ĩ
    0.07
    CISION
    0.07
    ocer
    0.07
    OLER
    0.07
    Activations Density 0.013%

    No Known Activations