© 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. 13195
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    ammel
    -0.08
    -span
    -0.08
    oded
    -0.07
    alami
    -0.07
    èĻ
    -0.06
     span
    -0.06
     cid
    -0.06
    acı
    -0.06
    ritch
    -0.06
    uden
    -0.06
    POSITIVE LOGITS
    оÑĢо
    0.08
    hur
    0.08
     Otherwise
    0.08
    Otherwise
    0.08
    鸦
    0.07
    else
    0.07
    个头
    0.07
     otherwise
    0.07
    ẻo
    0.07
    oje
    0.07
    Activations Density 0.021%

    No Known Activations