© 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. 43395
    Prev
    Next
    INDEX
    Explanations

    contraction or shrinking

    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
    -0.08
     halnya
    -0.08
    brahim
    -0.07
    icious
    -0.07
    erness
    -0.07
     obsta
    -0.07
    cht
    -0.07
    次çļĦ
    -0.07
     drauÃŁen
    -0.07
    ikhail
    -0.07
    POSITIVE LOGITS
    /exp
    0.09
    ively
    0.09
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.09
    AllWindows
    0.09
    缩
    0.08
    縮
    0.08
    /rem
    0.08
    /stretch
    0.08
    ive
    0.08
    /release
    0.07
    Activations Density 0.023%

    No Known Activations