© 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. 32702
    Prev
    Next
    INDEX
    Explanations

    make command

    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
    arium
    -0.07
    bay
    -0.07
    ÛķÙĪÛķ
    -0.06
     Maranh
    -0.06
    èĵĦ
    -0.06
    unden
    -0.06
    .currentTime
    -0.06
    æĺ¥æļĸ
    -0.06
    \'\
    -0.06
    UNCTION
    -0.06
    POSITIVE LOGITS
    anken
    0.08
    uku
    0.07
    eram
    0.07
    MediaType
    0.07
    ertz
    0.07
    åŃ£åĨĽ
    0.07
    ware
    0.06
    ennie
    0.06
     anyhow
    0.06
    ascar
    0.06
    Activations Density 0.001%

    No Known Activations