© 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. 29767
    Prev
    Next
    INDEX
    Explanations

    which introduces definitions or explanations

    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
    ation
    -0.14
    缸åħ³æ³ķå¾ĭ责任
    -0.09
    ãģ¾ãģ¾
    -0.09
    èĢĮåĸ»
    -0.09
    anmoins
    -0.09
    ÑģÑĤво
    -0.08
    ãģ¦
    -0.08
    uum
    -0.08
    ت
    -0.08
    tement
    -0.08
    POSITIVE LOGITS
    er
    0.20
    s
    0.12
    eru
    0.10
    erings
    0.09
    erÃŃa
    0.09
    erat
    0.09
    ÙħÙĥاÙĨ
    0.08
    ersten
    0.08
    ãĥ³
    0.08
    /her
    0.08
    Activations Density 0.170%

    No Known Activations