© 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. 26089
    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
    å¨Ĩ
    -0.09
    ooth
    -0.09
     Katz
    -0.08
    olen
    -0.07
    ording
    -0.07
    å½ķ
    -0.07
    av
    -0.07
    izr
    -0.07
    onor
    -0.07
    =[],
    -0.07
    POSITIVE LOGITS
    ä¹ĭéģ¥
    0.06
    ignano
    0.06
    wana
    0.06
    éľĨ
    0.06
    enes
    0.06
     Teresa
    0.06
    çļĦçİ°å®ŀ
    0.06
    iswa
    0.06
     Dana
    0.06
    ushima
    0.06
    Activations Density 0.000%

    No Known Activations