© 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. 27189
    Prev
    Next
    INDEX
    Explanations

    hybrids or crosses

    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
    åħ¨åħļ
    -0.07
    éļħ
    -0.07
    èĢĺ
    -0.07
    é¢Ħä»ĺ
    -0.07
    éĥ¨ç½²
    -0.06
    izedName
    -0.06
    ÏĦικ
    -0.06
    WithValue
    -0.06
    mps
    -0.06
    zam
    -0.06
    POSITIVE LOGITS
    æĿĤ交
    0.12
     hybrids
    0.11
     hybrid
    0.10
     hÃŃbr
    0.09
     offspring
    0.09
    ä¼ĺåĬ¿äºĴè¡¥
    0.09
     lai
    0.09
     гибÑĢи
    0.09
     mixing
    0.09
     resulting
    0.09
    Activations Density 0.037%

    No Known Activations