© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44845
    Prev
    Next
    INDEX
    Explanations

    Elixir, Vhdl, crochet, Flow

    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
    Descriptions
    -0.07
    ä¸įå¿ħè¦ģ
    -0.07
    å¹ķ
    -0.07
    cales
    -0.06
    odial
    -0.06
    oja
    -0.06
    _Impl
    -0.06
    odka
    -0.06
    ä½ķåĨµ
    -0.06
    orig
    -0.06
    POSITIVE LOGITS
    ä¹ĭåħī
    0.08
    ä¹ĭ声
    0.08
    çĻ¾äºº
    0.07
    就该
    0.07
    -focused
    0.07
    onet
    0.07
    inqu
    0.07
    ä¹ĭçªĹ
    0.07
    æĪĢ
    0.07
    -themed
    0.07
    Activations Density 0.622%

    No Known Activations