© 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. 26016
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming task

    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
    ä¼ļè¦ĭ
    -0.08
     thái
    -0.08
    ä»·æł¼åIJĪçIJĨ
    -0.07
    使çĶ¨æŶéĹ´
    -0.07
    第ä¸Ģ件äºĭ
    -0.07
    imbus
    -0.07
    èij¡èIJĦ
    -0.07
     vợ
    -0.07
    >Lorem
    -0.07
    okit
    -0.07
    POSITIVE LOGITS
     related
    0.08
     conject
    0.08
     integer
    0.08
    æķ°åĪĹ
    0.07
     OE
    0.07
    æĶ¶èĹı
    0.07
    çĥ¹
    0.07
    缸åħ³çļĦ
    0.07
     alternate
    0.07
     Related
    0.07
    Activations Density 0.058%

    No Known Activations