© 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. 49992
    Prev
    Next
    INDEX
    Explanations

    programming context parameter analysis

    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
    åݻ认è¯ģ
    -0.09
    $$$$
    -0.08
    BoundingClientRect
    -0.08
    pedia
    -0.08
    åħĥèµ·
    -0.08
    onsel
    -0.08
    OURCE
    -0.08
    _IA
    -0.08
    å¦ĩ女åĦ¿ç«¥
    -0.08
    é£ŀ鸣
    -0.08
    POSITIVE LOGITS
    at
    0.07
     (âĢ¦)
    0.06
    æĽ¿
    0.06
    è¡Į
    0.06
     leider
    0.06
    2
    0.06
     [âĢ¦
    0.06
    «
    0.06
    raj
    0.06
    èĭı
    0.06
    Activations Density 0.012%

    No Known Activations