© 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. 33789
    Prev
    Next
    INDEX
    Explanations

    `.h`, `,` file extensions

    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
    ignan
    -0.10
    enhagen
    -0.08
    为己
    -0.07
    ä¸Ĭæ·»
    -0.07
    .gwt
    -0.07
    åĬłéĩĮ
    -0.07
    ãģ¨ãģĦãģĨãģ¨
    -0.07
    ntag
    -0.07
    为éļ¾
    -0.07
    管çIJĨæĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    ä¸Ģä½ľ
    0.07
    é©ļ人
    0.06
    dyn
    0.06
     upstream
    0.06
    ix
    0.06
     Flame
    0.06
     Typ
    0.06
    еÑģÑĤ
    0.06
     benef
    0.06
     synthes
    0.06
    Activations Density 0.022%

    No Known Activations