© 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. 4179
    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
    uez
    -0.08
    er
    -0.08
    uyer
    -0.07
    imana
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    賦
    -0.07
    à¥ĭर
    -0.07
    dea
    -0.07
     lév
    -0.07
    UMB
    -0.07
    POSITIVE LOGITS
    oriously
    0.07
    hoven
    0.06
    èĢĮçŁ¥
    0.06
     Stiftung
    0.06
    getitem
    0.06
    åħįè´£
    0.06
    gaard
    0.06
    adz
    0.06
    é¦ĸåħĪ
    0.06
    容
    0.06
    Activations Density 0.000%

    No Known Activations