© 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. 58722
    Prev
    Next
    INDEX
    Explanations

    code blocks with curly braces

    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
    /root
    -0.07
    uai
    -0.07
    ua
    -0.07
    uis
    -0.07
    èĩ´çĶµ
    -0.06
     chua
    -0.06
    omin
    -0.06
    ĥĿ
    -0.06
    /]
    -0.06
    ÙİÙĨÙİا
    -0.06
    POSITIVE LOGITS
    пÑĸ
    0.07
    该类
    0.07
    atz
    0.07
    InBackground
    0.07
    ลัà¸ĩ
    0.06
     mir
    0.06
     mirrored
    0.06
    ostar
    0.06
    å¦ĤæѤä¸ĢæĿ¥
    0.06
     letterSpacing
    0.06
    Activations Density 0.001%

    No Known Activations