© 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. 15908
    Prev
    Next
    INDEX
    Explanations

    technical explanation

    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
    éĢļ常éľĢè¦ģ
    -0.07
    å¸ĥ伦
    -0.07
    书记åijĺ
    -0.07
    evers
    -0.07
    à¯Īயிலà¯į
    -0.07
     اÙĦاÙĤت
    -0.07
    对社ä¼ļ
    -0.07
    edores
    -0.07
    丽ä¸Ŀ
    -0.07
     yksity
    -0.07
    POSITIVE LOGITS
    çļĦä½ľçĶ¨æĺ¯
    0.09
    à¸Ĭà¹Īวยà¹ĥหà¹ī
    0.08
     essentially
    0.08
     helps
    0.08
    çļĦ帮åĬ©ä¸ĭ
    0.08
    à¸Ĭà¹Īวย
    0.08
    帮åĬ©
    0.08
    çļĦä½ľçĶ¨
    0.08
     giúp
    0.07
     help
    0.07
    Activations Density 0.104%

    No Known Activations