© 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. 24114
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    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
    åħļçļĦé¢Ĩ导
    -0.08
    spath
    -0.07
     supr
    -0.07
    ouv
    -0.07
    aling
    -0.07
    ady
    -0.07
    arella
    -0.07
    etail
    -0.07
    avig
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    POSITIVE LOGITS
     Viên
    0.07
    eke
    0.07
    prus
    0.07
    ê·ł
    0.07
    _attempt
    0.06
    egment
    0.06
    mod
    0.06
    rium
    0.06
    åħĪçĶ¨
    0.06
     preceded
    0.06
    Activations Density 0.013%

    No Known Activations