© 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. 17335
    Prev
    Next
    INDEX
    Explanations

    precision, detail, refinement, updates

    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
    lag
    -0.08
    à¸Ĭะ
    -0.08
    HIR
    -0.07
    鸳
    -0.07
    imple
    -0.07
    æµħæŀIJ
    -0.07
    èĢĮ论
    -0.07
    çĭ¬ç§Ģ
    -0.07
    otify
    -0.07
    åįĥå±±
    -0.07
    POSITIVE LOGITS
     refined
    0.10
     refine
    0.09
     refin
    0.08
     refinement
    0.08
    çīĪçļĦ
    0.08
    ç²¾
    0.08
    精緻
    0.08
    -than
    0.07
     than
    0.07
    -regexp
    0.07
    Activations Density 0.005%

    No Known Activations