© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    .php file extensions

    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
    .capitalize
    -0.07
    aka
    -0.07
    ajer
    -0.07
    รร
    -0.07
    anggung
    -0.07
    zas
    -0.07
    anz
    -0.07
    elli
    -0.07
    hati
    -0.06
    fam
    -0.06
    POSITIVE LOGITS
    -worthy
    0.08
    Ī
    0.08
    ä¸įçĿĢ
    0.08
    ç¬Ķä¸ĭçļĦ
    0.07
     représentant
    0.07
    æľ¬å°ı说
    0.07
    çada
    0.07
    pired
    0.07
    éĩĮåİ»
    0.06
    åł°
    0.06
    Activations Density 0.888%

    No Known Activations