© 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. 55439
    Prev
    Next
    INDEX
    Explanations

    mass-energy equivalence formula

    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
     Branche
    -0.08
    åĩĮéľĦ
    -0.08
    Į¨
    -0.08
    weer
    -0.08
    ieste
    -0.07
    åIJįæĢĿ
    -0.07
    ggi
    -0.07
    è½®
    -0.07
    婪
    -0.07
    vue
    -0.07
    POSITIVE LOGITS
     unthinkable
    0.08
     convertible
    0.08
     conversion
    0.07
    ä¸ĩçī©
    0.07
     conversions
    0.07
     energy
    0.07
    èĥ½éĩı
    0.07
    çĥŃèĥ½
    0.07
     Einstein
    0.07
    andel
    0.07
    Activations Density 0.001%

    No Known Activations