© 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. 10970
    Prev
    Next
    INDEX
    Explanations

    punctuation or end of clause

    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
    馨
    -0.06
    é«ĺ
    -0.06
    oins
    -0.06
    Ùħت
    -0.06
     http
    -0.06
    -http
    -0.06
    pred
    -0.06
    pike
    -0.06
    ä¸Ģè¡Į
    -0.06
    ä¿¡å¥ī
    -0.05
    POSITIVE LOGITS
     sister
    0.09
    å§Ĭ妹
    0.08
     ëĭ¨ëıħ
    0.08
    haj
    0.08
    erein
    0.08
    ä½ĵåĮĸ
    0.08
    ondon
    0.07
     Clone
    0.07
    åįģäºĶç«ł
    0.07
    Clone
    0.07
    Activations Density 0.441%

    No Known Activations