© 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. 28566
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    宸
    -0.07
    inox
    -0.07
    æ£ł
    -0.06
    ارد
    -0.06
    dest
    -0.06
    梳
    -0.06
    å½
    -0.06
    ä¸Ģéĺµ
    -0.06
    å±ķ
    -0.06
    EMS
    -0.06
    POSITIVE LOGITS
    herits
    0.09
    ặn
    0.08
    .Annotation
    0.07
    å¸¸åľ¨
    0.07
    巴赫
    0.07
    ода
    0.07
    uesto
    0.07
    eiten
    0.07
    ebo
    0.07
    lian
    0.07
    Activations Density 0.004%

    No Known Activations