© 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. 40927
    Prev
    Next
    INDEX
    Explanations

    html or string parsing

    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
    çĿĢä¸Ģé¢Ĺ
    -0.07
    /vector
    -0.06
    symbol
    -0.06
    ("/:
    -0.06
    ldb
    -0.06
    说好
    -0.06
    å±ĪæĮĩ
    -0.06
     unde
    -0.06
    .intValue
    -0.06
    个æĸ¹éĿ¢
    -0.06
    POSITIVE LOGITS
    ä¸Ģæ°Ķ
    0.10
    .lines
    0.08
     snippets
    0.08
    _EOF
    0.08
    åĮħåIJ«äºĨ
    0.08
     stringWith
    0.08
     excerpt
    0.07
    _lines
    0.07
    æİ§ç³»ç»Ł
    0.07
    çīĩ段
    0.07
    Activations Density 0.098%

    No Known Activations