© 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. 31607
    Prev
    Next
    INDEX
    Explanations

    section headers and documentation structure

    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
    AMED
    -0.09
    žen
    -0.08
    asil
    -0.08
    ÏĦηÏĤ
    -0.08
    天åīį
    -0.08
    ÄIJT
    -0.08
    å¸ĥæŀĹ
    -0.08
     Congratulations
    -0.08
    æĽ¿å°¼
    -0.08
    å°Ķå¤ļ
    -0.08
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.09
    )':
    0.07
     notable
    0.07
     dikkat
    0.06
    ä¸įåı¯æĢĿè®®
    0.06
    ÙĪرÙĩا
    0.06
    ç£¨çłº
    0.06
    举ä¾ĭ
    0.06
    åı¯èĥ½çļĦ
    0.06
    å®ŀéĻħåºĶçĶ¨
    0.06
    Activations Density 0.038%

    No Known Activations