© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    rating or value labels

    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
    纵
    -0.08
    trut
    -0.07
    å¾ľ
    -0.07
    åij¤
    -0.07
    essem
    -0.07
    ettino
    -0.07
    IVEN
    -0.07
    èse
    -0.07
    ä¹ĭéĥ½
    -0.07
    IDOS
    -0.07
    POSITIVE LOGITS
    oman
    0.07
    åĮºéķ¿
    0.07
    ause
    0.07
     masc
    0.06
    é¢Ĩä¼ļ
    0.06
     nanop
    0.06
    ס×Ļ
    0.06
    ct
    0.06
    ugas
    0.06
     dren
    0.06
    Activations Density 0.138%

    No Known Activations