© 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. 16074
    Prev
    Next
    INDEX
    Explanations

    .to together

    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
    ç«
    -0.07
    æĵħ
    -0.07
    ÙħÙĩ
    -0.07
    nil
    -0.07
    åĢ¾
    -0.07
    缤
    -0.07
    uttur
    -0.06
    å¼ķ以为
    -0.06
    fortune
    -0.06
    åĴ¯
    -0.06
    POSITIVE LOGITS
    stuff
    0.07
    зеÑĢ
    0.07
    zer
    0.07
    оÑĩÑĮ
    0.07
    çŃīç³»åĪĹ
    0.07
    _stuff
    0.07
     optimum
    0.06
    olut
    0.06
     conditions
    0.06
    etc
    0.06
    Activations Density 0.144%

    No Known Activations