© 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. 64120
    Prev
    Next
    INDEX
    Explanations

    clinical case reports, names, wire, copyright

    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
    âĢ¦âĢ¦ãĢĤ
    -0.08
    lobal
    -0.08
     **:**
    -0.08
     (**
    -0.07
    âĢ¦ãĢĤ
    -0.07
    ength
    -0.07
    porti
    -0.07
    vider
    -0.07
     ];
    -0.07
    __;
    -0.07
    POSITIVE LOGITS
    **”
    0.08
     bowiem
    0.08
    gether
    0.07
    æĺĵè´Ń
    0.07
     enim
    0.07
    ä¹Łç½¢
    0.06
    ä¼ļåĦ¿
    0.06
    ----------------------------------------------------------------------
    0.06
    ént
    0.06
    erior
    0.06
    Activations Density 0.053%

    No Known Activations