© 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. 9469
    Prev
    Next
    INDEX
    Explanations

    line processing

    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
    ç½ijåıĭä¸Ĭä¼ł
    -0.09
    éĺħè¯»æľ¬æĸĩåīį
    -0.09
    ستÙĩ
    -0.08
    Ùİاع
    -0.08
    .appspot
    -0.08
    ogos
    -0.08
    ä¸įèĥľæĶ¶
    -0.08
    yce
    -0.08
    .promise
    -0.08
    .nlm
    -0.08
    POSITIVE LOGITS
    wise
    0.08
     containing
    0.08
    /column
    0.08
    åĩºå¤Ħ
    0.07
    -wise
    0.06
    anen
    0.06
    ä¸ĬçļĦ
    0.06
    ãĢħãģ¨
    0.06
    -long
    0.06
    æĪĸå¤ļ
    0.06
    Activations Density 0.038%

    No Known Activations