© 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. 29214
    Prev
    Next
    INDEX
    Explanations

    programming keywords: class, typedef, struct

    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
    elloworld
    -0.06
    1
    -0.06
    ↵
    -0.06
    æĹ
    -0.06
    2
    -0.06
    haus
    -0.05
     S
    -0.05
    æĿĪ
    -0.05
     ir
    -0.05
    èĸ°
    -0.05
    POSITIVE LOGITS
    again
    0.18
     again
    0.17
     Again
    0.14
     novamente
    0.14
    Again
    0.14
    åĨįä¸Ģ次
    0.13
    åĨį次
    0.13
     nuovamente
    0.13
     nuevamente
    0.13
     опÑıÑĤÑĮ
    0.13
    Activations Density 0.031%

    No Known Activations