© 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. 26386
    Prev
    Next
    INDEX
    Explanations

    power generation, LCD panel, digital camera

    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
    齡
    -0.08
     vĩ
    -0.08
    manos
    -0.07
    诸èijĽ
    -0.07
    ixe
    -0.07
    漿
    -0.07
    è¾°
    -0.07
    aires
    -0.07
    íĺĦ
    -0.07
    é¶
    -0.07
    POSITIVE LOGITS
    éĥ¨åĪĨçļĦ
    0.13
     portion
    0.13
    éĥ¨åĪĨæĺ¯
    0.12
    éĥ¨åĪĨ
    0.12
     part
    0.12
    éĥ¨åĪĨãģ¯
    0.10
     component
    0.10
    è¿Ļéĥ¨åĪĨ
    0.10
     portions
    0.10
    éĥ¨åĪĨãĤĴ
    0.09
    Activations Density 0.207%

    No Known Activations