© 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. 41780
    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
    erder
    -0.07
     built
    -0.07
     Built
    -0.06
    ä»Ļ人
    -0.06
    Built
    -0.06
    built
    -0.06
    uilt
    -0.06
    ä¾µåħ¥
    -0.06
      ↵  ↵
    -0.06
    ¬ģ
    -0.06
    POSITIVE LOGITS
    stadt
    0.08
     Rena
    0.08
    utilise
    0.07
    леб
    0.07
    eluk
    0.07
    esco
    0.07
    abis
    0.07
    hung
    0.07
    ADX
    0.07
    å¿ĹæĪIJ
    0.07
    Activations Density 0.000%

    No Known Activations