© 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. 17658
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
    çıĬçıĬ
    -0.08
    é¾
    -0.07
    æħ¨
    -0.07
    iquid
    -0.07
    },'
    -0.07
    æĥĭæĥľ
    -0.07
    顶峰
    -0.07
    åĢ¦æĢł
    -0.07
    à¸ĺ
    -0.07
    éĨ
    -0.06
    POSITIVE LOGITS
     DISCLAIMER
    0.06
    éĩĩ
    0.06
    awk
    0.06
    åĪ©çī©
    0.06
    enny
    0.06
    lop
    0.06
    war
    0.06
    ä¸½å¨ľ
    0.06
    é¦ĻçļĦ
    0.06
    rael
    0.06
    Activations Density 0.002%

    No Known Activations