© 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. 22896
    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
    ÃŃp
    -0.08
    CommandLine
    -0.08
    amas
    -0.08
    åĩŃçĿĢ
    -0.07
    oted
    -0.07
    rensa
    -0.07
    è¿Ħ
    -0.07
    åĹĵ
    -0.07
    etus
    -0.07
    赫å°Ķ
    -0.07
    POSITIVE LOGITS
    ÙĪجÙĩ
    0.07
    åľĪåľĪ
    0.07
    ä¸įç»ı
    0.07
    -export
    0.07
    able
    0.07
     transfer
    0.07
    ä¸Ģæ³¢
    0.07
     Dang
    0.07
     export
    0.07
    ä½ľçĶ»
    0.07
    Activations Density 0.000%

    No Known Activations