© 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. 43494
    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
    年建
    -0.07
    飯
    -0.07
    ánt
    -0.06
    é¢Ŀ为
    -0.06
    åĢĴ
    -0.06
    éħĴåIJİ
    -0.06
    å±ħ
    -0.06
    éħĮ
    -0.06
    ouncement
    -0.06
    屯
    -0.06
    POSITIVE LOGITS
     Stap
    0.08
    åħ¬éģĵ
    0.08
    çIJ¦
    0.08
    å¬
    0.07
    ound
    0.07
    jeta
    0.07
    ÉĻc
    0.07
    جاÙħ
    0.07
    udge
    0.07
    çķľ
    0.07
    Activations Density 0.000%

    No Known Activations