© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57175
    Prev
    Next
    INDEX
    Explanations

    opens a dialog or window

    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
    etra
    -0.07
    uzzi
    -0.07
    ritz
    -0.07
    åľ°ä¸ĬçļĦ
    -0.07
    Prince
    -0.06
    acons
    -0.06
     medically
    -0.06
    .correct
    -0.06
     corrected
    -0.06
    ä¼ģä¸ļ形象
    -0.06
    POSITIVE LOGITS
    -che
    0.08
     sebelah
    0.08
    ä¹ħè¿Ŀ
    0.08
    ailable
    0.07
    åħ¨åĽ½åIJĦåľ°
    0.07
    ä¸Ĭ马
    0.07
    俨
    0.07
    ubb
    0.07
    å¹²ä»Ģä¹Ī
    0.07
    jang
    0.07
    Activations Density 0.082%

    No Known Activations