© 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. 29134
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and code snippets

    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
    伯ä¹IJ
    -0.07
    红åı¶
    -0.06
    è¾»
    -0.06
    ebro
    -0.06
    é²²
    -0.06
     proactive
    -0.06
    该åħ¬åı¸çļĦ
    -0.06
    ÅĻen
    -0.06
    alkan
    -0.05
    éķ¿åĩº
    -0.05
    POSITIVE LOGITS
    leans
    0.09
    åĵªåĦ¿
    0.08
    apura
    0.08
    tó
    0.08
    ifax
    0.08
    hav
    0.07
    åIJĦç§įåIJĦæł·çļĦ
    0.07
    atype
    0.07
    +')
    0.07
    upsi
    0.07
    Activations Density 0.001%

    No Known Activations