© 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. 56842
    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
    allo
    -0.08
    indsight
    -0.07
    νÏī
    -0.07
    жав
    -0.07
    ToFit
    -0.07
     spia
    -0.07
    luit
    -0.07
     Poverty
    -0.06
    Ø«ÙĬر
    -0.06
     veto
    -0.06
    POSITIVE LOGITS
    æĭīåħĭ
    0.08
    éĢĨ
    0.08
    pira
    0.07
    飬
    0.07
    èݱ德
    0.07
    æ¿ĥ
    0.07
    ziÄĻ
    0.06
    è¿Ļ个大
    0.06
    illions
    0.06
     leider
    0.06
    Activations Density 0.000%

    No Known Activations