© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22908
    Prev
    Next
    INDEX
    Explanations

    do or take

    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
    ãģ©ãģĵãĤį
    -0.07
    imia
    -0.07
    ¼
    -0.07
     же
    -0.06
    çĤ¹å¤´
    -0.06
    accès
    -0.06
    jeros
    -0.06
    èµ·è§ģ
    -0.06
    cion
    -0.06
    大å¦Ī
    -0.06
    POSITIVE LOGITS
     when
    0.10
     khi
    0.09
     regarding
    0.09
    when
    0.08
     during
    0.08
    樣çļĦ
    0.07
     for
    0.07
    à¸ļà¹īาà¸ĩ
    0.07
    aten
    0.07
    ersen
    0.07
    Activations Density 0.202%

    No Known Activations