© 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. 10662
    Prev
    Next
    INDEX
    Explanations

    code context with imports and requirements

    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
    hiri
    -0.07
    hin
    -0.07
    -0.07
    inish
    -0.07
    æĪijçļĦå¿ĥéĩĮ
    -0.07
    pi
    -0.06
    laps
    -0.06
    ira
    -0.06
    侯
    -0.06
    à¹Īà¸Ļ
    -0.06
    POSITIVE LOGITS
    å¹´æ¯ķä¸ļäºİ
    0.08
    åĭĻ
    0.08
    å¹´éĿĴ
    0.07
    endar
    0.07
     ("-
    0.07
    αιο
    0.07
     triá»ĩt
    0.07
    raid
    0.07
    éħ¸çĶľèĭ¦è¾£
    0.07
    RDD
    0.07
    Activations Density 0.013%

    No Known Activations