© 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. 32692
    Prev
    Next
    INDEX
    Explanations

    eigenvalues or exponents

    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
    é«ĺåĪĨ
    -0.08
    ½
    -0.07
    stra
    -0.07
     nbytes
    -0.07
    tle
    -0.07
    nage
    -0.06
    _EXTRA
    -0.06
    ковое
    -0.06
    çŃĿ
    -0.06
    é«ĺæ°´å¹³çļĦ
    -0.06
    POSITIVE LOGITS
     matur
    0.08
    èī²åĪĹ
    0.07
    agues
    0.07
    人æĹł
    0.07
     Tent
    0.07
     lari
    0.07
    etid
    0.07
    pectral
    0.07
    _APB
    0.07
    wart
    0.07
    Activations Density 0.004%

    No Known Activations