© 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. 21434
    Prev
    Next
    INDEX
    Explanations

    conclusion/report/verdict

    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
    plice
    -0.07
     ÐŁÐ¾ÐºÐ°Ð·Ð°
    -0.07
    hme
    -0.07
     ÐłÐ°Ð·Ñĥ
    -0.07
    .hm
    -0.07
    akk
    -0.07
    á»ĩu
    -0.07
    inä
    -0.07
    åįı
    -0.07
    valt
    -0.07
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.11
    对ä¸Ĭè¿°
    0.09
    åľ¨ä¸Ĭè¿°
    0.09
    ä¸Ĭè¿°ä½ľåĵģ
    0.08
    以ä¸Ĭ
    0.07
     aforementioned
    0.07
    åīįè¿°
    0.07
    دÙĬر
    0.07
    天ä»Ļ
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    Activations Density 0.299%

    No Known Activations