© 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. 51664
    Prev
    Next
    INDEX
    Explanations

    HTML/XML closing tags

    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
    ات
    -0.08
    icum
    -0.08
    eren
    -0.08
    ching
    -0.08
    åĿĬ
    -0.08
    aland
    -0.07
    acus
    -0.07
    ancell
    -0.07
    achen
    -0.07
    ensus
    -0.07
    POSITIVE LOGITS
     /*#__
    0.08
    gup
    0.07
    angsa
    0.07
    vio
    0.07
    quio
    0.07
    anzo
    0.06
    วà¸Ļ
    0.06
    大è§Ĥ
    0.06
     rede
    0.06
    à¥įरà¥Ģ
    0.06
    Activations Density 0.001%

    No Known Activations