© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    tags, class, files, touches, close

    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
    ãģ®ãĤĤãģ®
    -0.08
    cheng
    -0.07
    AMS
    -0.07
    awang
    -0.07
    çľĭä¸Ń
    -0.07
    _HEADERS
    -0.07
    å®ŀåľ¨å¤ª
    -0.07
    eneg
    -0.07
    丽åįİ
    -0.07
    _allowed
    -0.07
    POSITIVE LOGITS
     accordingly
    0.13
    为æѤ
    0.10
    缸åºĶ
    0.09
    对æѤ
    0.09
    缸åºĶçļĦ
    0.09
    åºĶè¿IJèĢĮçĶŁ
    0.08
     nisso
    0.08
     entsprechende
    0.07
     ÑģооÑĤвеÑĤ
    0.07
    缸æĩī
    0.07
    Activations Density 0.198%

    No Known Activations