© 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. 48988
    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
    isma
    -0.07
    ewise
    -0.06
    uku
    -0.06
    å¾Ĺåħ¶
    -0.06
    ãģ£ãģĿ
    -0.06
     Uz
    -0.06
    onna
    -0.06
    çľģä¸ĭ
    -0.06
    در
    -0.06
    pond
    -0.06
    POSITIVE LOGITS
    åħ¥éĩij
    0.08
    ÙĥÙĨ
    0.07
    ιδ
    0.07
    omé
    0.07
    upro
    0.07
    elj
    0.07
    elit
    0.07
    ograd
    0.07
    jih
    0.07
    ä¸įæ¼ı
    0.07
    Activations Density 0.000%

    No Known Activations