© 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. 9201
    Prev
    Next
    INDEX
    Explanations

    infinite stream, loop, or dimensions

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    erÃŃa
    -0.10
    翼翼
    -0.09
    sche
    -0.09
    ä¸į误
    -0.09
    åĽŀäºĭ
    -0.09
    ரிய
    -0.09
    Äħż
    -0.09
    zyst
    -0.09
    æĿ¥è¶Ĭ
    -0.08
    POSITIVE LOGITS
    -dimensional
    0.08
    -ish
    0.07
    esimal
    0.07
    /un
    0.07
    amous
    0.07
    æľī
    0.07
    Ùĩ
    0.06
    åĴĮ
    0.06
    ç¢į
    0.06
    तर
    0.06
    Activations Density 0.005%

    No Known Activations