© 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. 50173
    Prev
    Next
    INDEX
    Explanations

    exact matching

    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
    erland
    -0.08
    ä¸Ĭè¿°ä½ľåĵģ
    -0.07
    icons
    -0.07
    æĬĬåŃ¦ä¹ł
    -0.07
    elay
    -0.07
    ipherals
    -0.07
    åŁºç¡ĢæĢ§
    -0.07
     [+]
    -0.07
    .charCodeAt
    -0.07
    _icon
    -0.07
    POSITIVE LOGITS
     exact
    0.09
    exact
    0.09
     Exact
    0.08
    Exact
    0.08
    精确
    0.08
     exactly
    0.07
    约å®ļ
    0.07
    dit
    0.07
    actly
    0.07
    éĽĢ
    0.07
    Activations Density 0.002%

    No Known Activations