© 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. 50556
    Prev
    Next
    INDEX
    Explanations

    max visualizations to parameters

    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
    vertise
    -0.08
    .interpolate
    -0.08
     khóa
    -0.07
    cad
    -0.07
    mann
    -0.07
    dac
    -0.07
    人æ°ij代表大ä¼ļ常åĬ¡å§Ķåijĺä¼ļ
    -0.07
     igien
    -0.07
     cad
    -0.07
    oled
    -0.07
    POSITIVE LOGITS
    åıij
    0.06
    age
    0.06
    è¿«åĪĩéľĢè¦ģ
    0.06
    åŀĭ
    0.05
    é¦ĸæī¹
    0.05
    å¤ļéĩį
    0.05
    ä¸įå®ŀ
    0.05
     berb
    0.05
     MULT
    0.05
    丼
    0.05
    Activations Density 0.027%

    No Known Activations