© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 34319
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iaan
    -0.08
    å¦ĻçļĦ
    -0.07
     Worth
    -0.07
     onStart
    -0.06
    amet
    -0.06
     worth
    -0.06
    ç¼ĸ
    -0.06
     Labrador
    -0.06
    æ°ı
    -0.06
    iele
    -0.06
    POSITIVE LOGITS
    oleh
    0.08
    csr
    0.07
    lant
    0.07
    æŁ¥çľĭåħ¨éĥ¨
    0.07
    ãĤ¸ãĥ¼
    0.07
    ÑĩеÑģ
    0.07
    гÑĸд
    0.07
    alle
    0.07
    DEN
    0.07
    anty
    0.07
    Activations Density 0.000%

    No Known Activations