© 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. 22944
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ipan
    -0.10
    éton
    -0.09
    rans
    -0.08
    aday
    -0.08
    اÙĨات
    -0.08
    -0.08
    andai
    -0.08
    ĶĦ
    -0.08
    次éĺħ读
    -0.08
    akon
    -0.08
    POSITIVE LOGITS
    WND
    0.07
    éĮ
    0.06
    شت
    0.06
    er
    0.06
    åįĹå®ī
    0.06
    âĢ¦
    0.06
    Ñīе
    0.06
    escu
    0.06
    鼨
    0.06
    éĤ£ä¸Ģ
    0.06
    Activations Density 0.000%

    No Known Activations