© 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. 28730
    Prev
    Next
    INDEX
    Explanations

    Chinese, nvarchar, DL

    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
    tures
    -0.11
    ing
    -0.09
    ت
    -0.08
    sver
    -0.08
    s
    -0.08
    ÏĤ
    -0.08
    ejo
    -0.08
    nows
    -0.08
    sWith
    -0.08
    Ø©
    -0.08
    POSITIVE LOGITS
    ìį¨
    0.15
    Ùĩ
    0.12
    ëį°ìļĶ
    0.11
    ãĥ³
    0.10
    ãĤĪãģĨãģ«
    0.09
    à¸ģาร
    0.09
    u
    0.09
    èĩªå·±
    0.09
    اء
    0.09
    à¸ģารà¹Ģรียà¸Ļ
    0.08
    Activations Density 0.001%

    No Known Activations