© 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. 41236
    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
    orne
    -0.08
    สà¸Ļิà¸Ĺ
    -0.07
    omencl
    -0.07
    ordin
    -0.07
    DEST
    -0.07
    è¿ĩå¤ľ
    -0.07
    ielle
    -0.06
    é¾Ļæ¹ĸ
    -0.06
    andid
    -0.06
    -serif
    -0.06
    POSITIVE LOGITS
    czy
    0.09
    èĩ
    0.08
    accio
    0.08
    izzo
    0.08
    ëĮĢë¡ľ
    0.08
    ipsis
    0.07
    áció
    0.07
    cs
    0.07
    cba
    0.07
    å¸Ŀ
    0.07
    Activations Density 0.000%

    No Known Activations