© 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. 8769
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and operators

    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
    streams
    -0.07
    ERC
    -0.07
     streams
    -0.07
    _emit
    -0.07
    allar
    -0.07
     streamed
    -0.07
    禧
    -0.07
    åIJĦè¡ĮåIJĦä¸ļ
    -0.06
    stream
    -0.06
    à´Ļàµįà´Ļ
    -0.06
    POSITIVE LOGITS
    åIJ«æľīçļĦ
    0.08
    åIJ«
    0.08
    anax
    0.07
    ä¸įèµ·
    0.07
    odies
    0.07
    rending
    0.07
    avic
    0.06
     keting
    0.06
     cre
    0.06
    åıĭåĸĦ
    0.06
    Activations Density 0.001%

    No Known Activations