© 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. 20175
    Prev
    Next
    INDEX
    Explanations

    CO₂

    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
    als
    -0.07
    most
    -0.07
    ani
    -0.07
     courant
    -0.07
    hood
    -0.07
    /or
    -0.07
    ments
    -0.06
    ously
    -0.06
    ymous
    -0.06
    uguay
    -0.06
    POSITIVE LOGITS
    ़
    0.10
    ython
    0.09
    0.08
    िश
    0.08
    ITICAL
    0.08
    ylation
    0.08
    ieza
    0.08
    à¥ĩ
    0.08
    åħ¨å¿ĥåħ¨æĦı
    0.07
    ajib
    0.07
    Activations Density 0.013%

    No Known Activations