© 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. 9878
    Prev
    Next
    INDEX
    Explanations

    energy concepts and contexts

    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
    essor
    -0.09
    auer
    -0.08
    sWith
    -0.08
    å¾Ĺä¸Ĭ
    -0.08
     شدÙĨ
    -0.08
    itioner
    -0.07
    ellaneous
    -0.07
    ï¸ı
    -0.07
    entifier
    -0.07
    äºĨä¸Ģçľ¼
    -0.07
    POSITIVE LOGITS
    psilon
    0.10
    lixir
    0.09
    /power
    0.08
    -saving
    0.08
    dze
    0.08
    loquent
    0.08
    quelle
    0.08
    /time
    0.08
    Ù°
    0.08
    ÃŃf
    0.08
    Activations Density 0.024%

    No Known Activations