© 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. 16368
    Prev
    Next
    INDEX
    Explanations

    javascript code delimiters

    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
    精彩åĨħ容
    -0.09
    ##_
    -0.09
    еÑĢÑĮ
    -0.09
     sake
    -0.09
    wok
    -0.09
    ÛĮØ´
    -0.08
    wijs
    -0.08
    ardown
    -0.08
     obsta
    -0.08
     @$
    -0.08
    POSITIVE LOGITS
     “
    0.07
     impro
    0.06
    ´
    0.06
    æĮģ
    0.06
    æĨ¾
    0.06
    0.06
     complement
    0.06
    ness
    0.06
    Ģ
    0.06
    ç¦ģ
    0.05
    Activations Density 0.026%

    No Known Activations