© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8693
    Prev
    Next
    INDEX
    Explanations

    ending a process or period

    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
    ORM
    -0.07
    _ONCE
    -0.07
    åįĵè¶ĬçļĦ
    -0.07
    igid
    -0.07
    ä»İè¿Ļ个
    -0.07
    éĩıåĬĽ
    -0.07
    ëį°
    -0.07
     tarda
    -0.07
    nado
    -0.07
    ellini
    -0.07
    POSITIVE LOGITS
    ä¸įäºĨ
    0.11
    ä¸įäºĨäºĨ
    0.10
    ä¸įäºĨçļĦ
    0.09
    à¸Ķà¹īวยà¸ģาร
    0.09
    /end
    0.09
    สิà¹īà¸Ļ
    0.09
     xuôi
    0.08
    erci
    0.08
     with
    0.08
    swith
    0.08
    Activations Density 0.108%

    No Known Activations