© 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. 25382
    Prev
    Next
    INDEX
    Explanations

    coding language keywords

    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
    erland
    -0.07
    ãģ¾ãģı
    -0.07
    ogn
    -0.07
    ile
    -0.07
    strap
    -0.07
    è¿ĻæĬĬ
    -0.06
    åĽ´æĶ»
    -0.06
    tle
    -0.06
    cape
    -0.06
    ourage
    -0.06
    POSITIVE LOGITS
    çİ
    0.07
    ãĢĸ
    0.07
    为ä¿ĥè¿Ľ
    0.07
    âng
    0.07
    æ¸ħæ³ī
    0.07
    meld
    0.07
    éĿĵ
    0.06
    fro
    0.06
    atera
    0.06
    klin
    0.06
    Activations Density 0.016%

    No Known Activations