© 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. 20966
    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
    并ä¸įéļ¾
    -0.07
    éĿŀåIJĮ
    -0.07
    ä¸Ģ对ä¸Ģ
    -0.06
    ancar
    -0.06
    ://{
    -0.06
    饮
    -0.06
    xca
    -0.06
    åĩ»
    -0.06
    ìĨį
    -0.06
    cart
    -0.06
    POSITIVE LOGITS
    çĻ¾åĪĨä¹ĭ
    0.11
     percentages
    0.10
    åįłæĢ»
    0.10
    åįłæ¯Ķ
    0.09
    æĢ»è®¡
    0.09
    percentage
    0.08
    åįł
    0.08
    %(
    0.08
    %%
    0.08
    åIJĪè¨Ī
    0.08
    Activations Density 0.076%

    No Known Activations