© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    energy formulas and units

    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
    n
    -0.08
    l
    -0.08
    lah
    -0.08
    ss
    -0.08
    nya
    -0.08
    ness
    -0.07
    s
    -0.07
    ized
    -0.07
    m
    -0.07
    so
    -0.07
    POSITIVE LOGITS
    Ø©
    0.12
    ingang
    0.11
    iras
    0.10
    Ùĭ
    0.10
    urope
    0.10
    ëģĶ
    0.10
    psilon
    0.10
    eson
    0.10
    lixir
    0.10
    nergy
    0.10
    Activations Density 0.004%

    No Known Activations