© 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. 51302
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    pliers
    -0.07
    éħį
    -0.07
    ড়া
    -0.07
    åľ¨æĦı
    -0.07
    ligt
    -0.07
    æŃ¤èµ·
    -0.07
    ç½Ĺå¾·
    -0.07
    ])]
    -0.07
    èĭ¦å¿ĥ
    -0.06
    空置
    -0.06
    POSITIVE LOGITS
    éŃħ
    0.07
     trate
    0.07
    èĮµ
    0.06
    åªĽ
    0.06
    Emp
    0.06
    åľ¨è¿Ļ个ä¸ĸçķĮä¸Ĭ
    0.06
     jamás
    0.06
    iven
    0.06
     verle
    0.06
     kian
    0.06
    Activations Density 0.047%

    No Known Activations