© 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. 38829
    Prev
    Next
    INDEX
    Explanations

    recent or upcoming events

    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
    &apos
    -0.08
     initially
    -0.08
    -0.07
    etro
    -0.07
    ادÙħ
    -0.07
     specifically
    -0.07
    åŁºæľ¬åİŁçIJĨ
    -0.07
    éĻ
    -0.07
    adier
    -0.07
     traditionally
    -0.07
    POSITIVE LOGITS
    -looking
    0.13
    ly
    0.13
    ÃŃsimo
    0.12
    ness
    0.11
    mente
    0.11
    /false
    0.11
    ÃŃssimo
    0.10
    issime
    0.10
    ÃŃss
    0.10
    (?)
    0.10
    Activations Density 1.340%

    No Known Activations