© 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. 27095
    Prev
    Next
    INDEX
    Explanations

    mesh structures and uses

    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
    ếm
    -0.08
    åı¸éķ¿
    -0.08
    ebin
    -0.08
    plevel
    -0.08
    iface
    -0.08
    gether
    -0.08
    ç½®åľ°
    -0.08
    ãģ£ãģ±
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    brero
    -0.07
    POSITIVE LOGITS
    ed
    0.11
    Ø©
    0.10
    itecture
    0.09
    ing
    0.09
    ung
    0.08
    ness
    0.08
    ation
    0.08
    making
    0.08
    (mesh
    0.08
    ification
    0.07
    Activations Density 0.016%

    No Known Activations