© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16551
    Prev
    Next
    INDEX
    Explanations

    structural tokens and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     another
    -0.08
    åı¦ä¸Ģ
    -0.08
    åı¦ä¸Ģ个
    -0.08
    ÑĢÑĥг
    -0.07
     versa
    -0.07
    linger
    -0.07
    ibal
    -0.07
    çł°
    -0.07
    åĪ°å°¾
    -0.07
    oten
    -0.07
    POSITIVE LOGITS
    ink
    0.08
    ashian
    0.07
     اÙĦÙħشترÙĥ
    0.07
     Rush
    0.07
    åĭ¾
    0.06
    DED
    0.06
    æĩĤçļĦ
    0.06
     dis
    0.06
    ovid
    0.06
    trag
    0.06
    Activations Density 0.088%

    No Known Activations