© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    technical configuration

    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
    åĴ¬çīĻåĪĩ
    -0.08
     juxtap
    -0.08
     faithfully
    -0.07
    åĪĨç«ĭ
    -0.07
     loosely
    -0.07
    ä½ķçŃī
    -0.06
    ixo
    -0.06
    ix
    -0.06
    semi
    -0.06
    zig
    -0.06
    POSITIVE LOGITS
    åij½ä»¤
    0.08
     (`
    0.08
     command
    0.08
    çļĦåij½ä»¤
    0.08
    -command
    0.08
    (`
    0.08
    åIJį为
    0.08
    代çłģå¦Ĥä¸ĭ
    0.08
    ossier
    0.07
    æĮĩå®ļ
    0.07
    Activations Density 0.830%

    No Known Activations