© 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. 46290
    Prev
    Next
    INDEX
    Explanations

    numeric digits and 'two'

    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
    NX
    -0.07
    æ·±æµħ
    -0.06
    wa
    -0.06
    ä¼°
    -0.06
     Shed
    -0.06
    èģĮä¸ļ
    -0.06
    估计
    -0.06
    -O
    -0.06
     Wagner
    -0.06
    é¢Ħä¼°
    -0.06
    POSITIVE LOGITS
    à¸Ľà¸IJม
    0.08
    åħ¶ä¸ī
    0.08
    /simple
    0.08
    åħ¶äºĮ
    0.08
    åı¯çĪ±çļĦå°ı
    0.08
    ews
    0.07
    å°įæĩī
    0.07
     famously
    0.07
    -simple
    0.07
     Fili
    0.07
    Activations Density 0.009%

    No Known Activations