© 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. 47918
    Prev
    Next
    INDEX
    Explanations

    material models

    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
    avu
    -0.06
    lesi
    -0.06
    .Utility
    -0.06
    otis
    -0.06
     bá»ij
    -0.06
    fy
    -0.06
    ingi
    -0.06
     ×ĸ×ķ
    -0.06
    ĥģ
    -0.06
    adona
    -0.06
    POSITIVE LOGITS
    perm
    0.08
    NASDAQ
    0.07
    engah
    0.07
    inach
    0.07
    urkan
    0.07
    ceo
    0.07
    /terms
    0.07
    .www
    0.07
    ình
    0.07
    rase
    0.07
    Activations Density 0.001%

    No Known Activations