© 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. 7566
    Prev
    Next
    INDEX
    Explanations

    localization, invention, ancy, renewal

    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
    PRECATED
    -0.11
    SKTOP
    -0.10
    anmar
    -0.10
    raphics
    -0.10
    entifier
    -0.09
    \Active
    -0.09
    anoia
    -0.09
    ÏĦιά
    -0.09
    .wikipedia
    -0.09
    -marker
    -0.09
    POSITIVE LOGITS
    Âł
    0.07
    0.07
    2
    0.07
    (
    0.06
     .
    0.06
    1
    0.06
     $
    0.06
    D
    0.06
    A
    0.06
    .
    0.06
    Activations Density 5.089%

    No Known Activations