© 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. 29942
    Prev
    Next
    INDEX
    Explanations

    deform, deflect, compress

    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
    顾
    -0.07
    _refresh
    -0.07
    æ³¼
    -0.07
    icos
    -0.06
    è¯ŀ
    -0.06
    _death
    -0.06
    leanup
    -0.06
    .cluster
    -0.06
    ëĸł
    -0.06
    ulah
    -0.06
    POSITIVE LOGITS
    伸éķ¿
    0.08
    дли
    0.08
    ansch
    0.08
     deform
    0.08
    /extensions
    0.07
    ä¸īå°º
    0.07
    pring
    0.07
    弹簧
    0.07
    .autoconfigure
    0.07
    è®°ä¸ĭ
    0.07
    Activations Density 0.008%

    No Known Activations