© 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. 11935
    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
    天河
    -0.07
    é¦Ļæł¼éĩĮæĭī
    -0.07
    atisfied
    -0.07
     hereby
    -0.06
    å®ŀéªĮ
    -0.06
    åįĥåŃĹ
    -0.06
    oul
    -0.06
    attr
    -0.06
    èĢĮå·²
    -0.06
    éķ¿äºĨ
    -0.06
    POSITIVE LOGITS
     tông
    0.08
    ÎĹΣ
    0.08
    zos
    0.07
    Amministrazione
    0.07
    Mappings
    0.07
    º
    0.07
    osten
    0.07
    zinha
    0.07
    á»Ļng
    0.07
    stellungs
    0.07
    Activations Density 0.000%

    No Known Activations