© 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. 14923
    Prev
    Next
    INDEX
    Explanations

    digits and punctuation following characters

    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
    itt
    -0.07
    åĬ¡
    -0.07
    æīį被
    -0.07
    ivet
    -0.07
    åĩłå¤§
    -0.06
    zin
    -0.06
    اÛĮد
    -0.06
    è§Ħ模以ä¸Ĭ
    -0.06
    .constants
    -0.06
     rel
    -0.06
    POSITIVE LOGITS
    å¥Īä½ķ
    0.08
    产åĵģå±ķ示
    0.08
    ä¸į移
    0.07
    å¨ģ士
    0.07
     Startseite
    0.07
    cce
    0.07
    diy
    0.07
    ersist
    0.07
    ä¸īæĽ´
    0.06
    (side
    0.06
    Activations Density 0.001%

    No Known Activations