© 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. 14179
    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
    åĴĮåIJİ
    -0.06
    erta
    -0.06
    ington
    -0.06
    å¿ĺè®°äºĨ
    -0.06
    é£İå°ĺ
    -0.06
    天çĦ¶
    -0.06
    illard
    -0.06
    -0.06
    åĽłæѤ
    -0.06
    esen
    -0.06
    POSITIVE LOGITS
    åģļ个
    0.08
    InstanceOf
    0.07
    rawer
    0.07
    adiator
    0.07
    umbing
    0.07
     berm
    0.07
     khoái
    0.07
    upes
    0.07
    檸
    0.07
    _detector
    0.07
    Activations Density 0.000%

    No Known Activations