© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34926
    Prev
    Next
    INDEX
    Explanations

    change indicators `+` and `b`

    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
    Negative Logits
    etc
    -0.08
    thers
    -0.06
    sson
    -0.06
    -basket
    -0.06
    _
    -0.06
    /mac
    -0.06
    es
    -0.06
    ä¸Ģ票
    -0.06
    à¥įस
    -0.06
     etc
    -0.06
    POSITIVE LOGITS
    ayani
    0.09
    uil
    0.08
    åij¨å²ģ以ä¸Ĭ
    0.08
    YG
    0.07
    hir
    0.07
    à¹Ģà¸ģลà¹īา
    0.07
    accordo
    0.07
    å°Ĭéĩį
    0.07
    utus
    0.07
    é³Į
    0.07
    Activations Density 0.004%

    No Known Activations