© 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. 56868
    Prev
    Next
    INDEX
    Explanations

    relative subgroups

    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
    人工
    -0.07
    ter
    -0.07
    å¾Ĺ人
    -0.07
     Otherwise
    -0.07
    ×Ķ׾
    -0.06
    rossover
    -0.06
    缮åīį没æľī
    -0.06
    åIJĮåIJį
    -0.06
    .iter
    -0.06
     Satur
    -0.06
    POSITIVE LOGITS
    nox
    0.08
    غار
    0.07
    å·¥ä½ľåĴĮçĶŁæ´»
    0.07
    ä¸īæ°´
    0.07
    SPATH
    0.07
    Paths
    0.07
    æĭĶ
    0.07
    ieux
    0.07
    åľ¨åı°
    0.07
    apsed
    0.07
    Activations Density 0.003%

    No Known Activations