© 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. 14485
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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
    è·¯åĮĹ
    -0.09
    è·¯ä¸ľ
    -0.09
    è·¯åįĹ
    -0.08
    è´
    -0.07
     ($.
    -0.07
    laat
    -0.07
    ãģ¾ãģ¾
    -0.07
    å¿Ĺ强
    -0.07
    Enlarge
    -0.07
    lio
    -0.07
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.07
    aps
    0.07
    abis
    0.07
    æīĢåľ¨åľ°
    0.07
    åĨ³å®ļæĺ¯åIJ¦
    0.06
    åĴĮåħ¶
    0.06
    amed
    0.06
    atisfaction
    0.06
    lectron
    0.06
    å¤ļå°ij
    0.06
    Activations Density 0.008%

    No Known Activations