© 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. 63544
    Prev
    Next
    INDEX
    Explanations

    plasma discharge lamps

    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
    ç¾Ĭ
    -0.07
    ishi
    -0.07
     Fold
    -0.06
    éľī
    -0.06
     fold
    -0.06
     storage
    -0.06
    storage
    -0.06
    å®ŀéĻħè¡ĮåĬ¨
    -0.06
     tread
    -0.06
    egasus
    -0.06
    POSITIVE LOGITS
    èį§
    0.09
    æĪ·æĻĵ
    0.09
    çĦ°
    0.08
    çģ«çĦ°
    0.08
    èĨĽ
    0.08
    urn
    0.08
    宵
    0.08
     emitir
    0.08
    .dictionary
    0.08
     Pistol
    0.08
    Activations Density 0.016%

    No Known Activations