© 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. 32632
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     Brief
    -0.07
    åĴĮ丰å¯ĮçļĦ
    -0.07
    ating
    -0.07
    æĸĩåĮĸä¼łæĴŃæľīéĻIJåħ¬åı¸
    -0.06
    åī¥
    -0.06
     briefly
    -0.06
     praw
    -0.06
    ç¾²
    -0.06
    itora
    -0.06
     brief
    -0.06
    POSITIVE LOGITS
    orda
    0.08
    alp
    0.07
    OGO
    0.07
    è¯Ħ论åĨħ容
    0.07
    æıIJé«ĺèĩªèº«
    0.07
    umd
    0.07
    avel
    0.07
    ogo
    0.07
    OutOf
    0.07
    UpDown
    0.07
    Activations Density 0.025%

    No Known Activations