© 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. 39296
    Prev
    Next
    INDEX
    Explanations

    items or lists

    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
    èĬ±æľ¨
    -0.06
    ILLE
    -0.06
    enho
    -0.06
     |_|
    -0.06
    quÃŃ
    -0.06
     Alison
    -0.06
    _^
    -0.06
    mien
    -0.06
    ç»Ķ
    -0.06
    qü
    -0.06
    POSITIVE LOGITS
     Telekom
    0.07
    oki
    0.07
    _ctx
    0.07
    ci
    0.07
    oni
    0.07
    ctp
    0.07
    inch
    0.07
    ilde
    0.07
    ç½²
    0.07
    amarin
    0.07
    Activations Density 0.018%

    No Known Activations