© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50337
    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
    èIJ±
    -0.08
    ORA
    -0.07
     há»ķ
    -0.07
     ÐĶобÑĢ
    -0.07
    permissions
    -0.06
    regions
    -0.06
    çĴĥ
    -0.06
    hte
    -0.06
    åħ·æľīçĭ¬ç«ĭ
    -0.06
    statt
    -0.06
    POSITIVE LOGITS
    sdk
    0.08
    ablemente
    0.07
    彿
    0.07
    ãĥĦãĥ¼
    0.07
    丹丹
    0.07
    èģĮ
    0.07
    ÎijΣ
    0.07
     inputStream
    0.07
    äºĶ项
    0.06
    ÙĥÙĬÙĦ
    0.06
    Activations Density 0.000%

    No Known Activations