© 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. 58888
    Prev
    Next
    INDEX
    Explanations

    GSM version number

    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
     ($)
    -0.07
    idia
    -0.07
    /misc
    -0.07
    i
    -0.07
    /downloads
    -0.06
    /stretch
    -0.06
    atham
    -0.06
     retire
    -0.06
     |_|
    -0.06
    (.)
    -0.06
    POSITIVE LOGITS
    ffffffff
    0.08
     realtime
    0.07
     factur
    0.07
     efficac
    0.07
    赶è¶ħ
    0.07
    ä¸Ģåħ±
    0.07
    iculares
    0.07
    allon
    0.06
    ampled
    0.06
    andes
    0.06
    Activations Density 0.065%

    No Known Activations