© 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. 42516
    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
    æī«æıı
    -0.08
    witz
    -0.08
    ühlt
    -0.08
     Spiegel
    -0.08
    ãĥ¼ãĥĹ
    -0.07
    eker
    -0.07
    ç»į
    -0.07
    ahoma
    -0.07
    æıļ
    -0.07
    oint
    -0.07
    POSITIVE LOGITS
    表示èĩªå·±
    0.07
    صØŃ
    0.07
    odo
    0.06
    èĢĮ代ä¹ĭ
    0.06
    èIJ½å®ŀ好
    0.06
    åŀ
    0.06
    æŁ¥çIJĨ
    0.06
     Larson
    0.06
    sgi
    0.06
    _tid
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.