© 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. 27595
    Prev
    Next
    INDEX
    Explanations

    where followed by math symbols

    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
    å®ĥ对
    -0.08
     Trì
    -0.07
    lickr
    -0.07
    locker
    -0.07
    åĬłä¹ĭ
    -0.07
    ÛĮدÙĨ
    -0.07
    -send
    -0.07
    tar
    -0.07
     اÙĦÙĪر
    -0.07
    steller
    -0.07
    POSITIVE LOGITS
    alat
    0.08
    åij»
    0.07
    è¦ģ注æĦıçļĦæĺ¯
    0.07
    erschap
    0.07
    ëĭ¤
    0.07
     amalg
    0.07
    ashed
    0.07
    绵绵
    0.07
    alj
    0.07
    ince
    0.06
    Activations Density 0.010%

    No Known Activations