© 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. 47038
    Prev
    Next
    INDEX
    Explanations

    typical use/method/structure

    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
    -0.10
    اء
    -0.09
    utip
    -0.08
    manship
    -0.08
    egen
    -0.08
    xious
    -0.08
    allah
    -0.08
    /OR
    -0.08
    osso
    -0.08
     kepentingan
    -0.08
    POSITIVE LOGITS
    ity
    0.14
    weise
    0.11
    -looking
    0.10
    ities
    0.09
    cy
    0.09
    idades
    0.08
    ITY
    0.08
    åľ°æĬĬ
    0.08
    ized
    0.08
    erweise
    0.08
    Activations Density 0.033%

    No Known Activations