© 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. 20272
    Prev
    Next
    INDEX
    Explanations

    automatically generated code or components

    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
    ething
    -0.07
    essa
    -0.07
    essim
    -0.07
    åĩºå¥ĩ
    -0.06
    irected
    -0.06
     laat
    -0.06
     .....
    -0.06
    书åıĭ
    -0.06
    retty
    -0.06
     Forg
    -0.06
    POSITIVE LOGITS
    åŁĶ
    0.08
    称ä¹ĭ为
    0.08
    gnu
    0.08
    ÙĪÙĬر
    0.08
    è°ĵä¹ĭ
    0.07
    EFE
    0.07
    ssc
    0.07
    ÑĭÑĢ
    0.07
    modify
    0.07
    olib
    0.07
    Activations Density 0.448%

    No Known Activations