© 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. 24715
    Prev
    Next
    INDEX
    Explanations

    ; punctuation

    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
    esimo
    -0.08
    åĴĮ好
    -0.08
    vÄĽ
    -0.08
    ANCEL
    -0.07
    каÑĢ
    -0.07
    aphore
    -0.07
    å®ŀéĻħåºĶçĶ¨
    -0.07
    ignon
    -0.07
    %E
    -0.07
    å¤ļä¸ĢçĤ¹
    -0.07
    POSITIVE LOGITS
    yon
    0.07
    ly
    0.07
    ãģ¤ãģ®
    0.07
    å¾Ĺ主
    0.07
    åį¡è·¯
    0.06
    اÙĦتÙĩا
    0.06
    çªĸ
    0.06
    yo
    0.06
    ï¸İ
    0.06
    Ĭ
    0.06
    Activations Density 0.093%

    No Known Activations