© 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. 18874
    Prev
    Next
    INDEX
    Explanations

    reading lines from files

    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
    åĩĨ
    -0.07
    ä¸Ģçľ¼
    -0.06
    licing
    -0.06
    ä¼¼éĶ¦
    -0.06
    ä¸įç¡®å®ļ
    -0.06
    RPC
    -0.06
    å±ķçİ°åĩºäºĨ
    -0.06
    ogonal
    -0.06
    è§Ĥ
    -0.06
    ä¸ŃæĮĩåĩº
    -0.06
    POSITIVE LOGITS
    OrNull
    0.08
    _until
    0.08
    CONTENT
    0.07
    é¥
    0.07
    UTH
    0.07
    rap
    0.07
    .readLine
    0.07
    åĨĽåĽ¢
    0.07
    -lined
    0.07
    ediator
    0.07
    Activations Density 0.097%

    No Known Activations