© 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. 19697
    Prev
    Next
    INDEX
    Explanations

    variables and math equations

    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
    illo
    -0.08
    _SYN
    -0.08
    缺
    -0.07
    è¦ģæ±ĤåIJĦ
    -0.07
    aight
    -0.07
     Unsupported
    -0.07
    iola
    -0.07
    ober
    -0.07
    åĨľçī§
    -0.06
    baÅŁ
    -0.06
    POSITIVE LOGITS
    åĪĨ许
    0.08
    uhu
    0.07
    odaw
    0.07
    ESE
    0.07
    .zz
    0.07
    ä¼łæĿ¥çļĦ
    0.07
    çķĻé¦Ļ
    0.07
    elpers
    0.07
     Bade
    0.07
    çĺ¢
    0.06
    Activations Density 0.005%

    No Known Activations