© 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. 7399
    Prev
    Next
    INDEX
    Explanations

    body and science

    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
     mòn
    -0.07
    APA
    -0.07
    ãĥĸãĥ¬
    -0.07
    upro
    -0.07
    硬æľĹ
    -0.07
    åľ¨é¡¹çĽ®
    -0.07
     Arbor
    -0.07
     Sense
    -0.07
    è¿ŁéĴĿ
    -0.07
    chy
    -0.07
    POSITIVE LOGITS
    åªĴ
    0.07
     armon
    0.07
    æĹ©æķĻ
    0.07
    管åĨħ
    0.07
    åı¤åħ¸
    0.07
    å£ģ
    0.07
    å£ģæĮĤ
    0.06
    åħIJ
    0.06
     Gug
    0.06
     harmon
    0.06
    Activations Density 0.001%

    No Known Activations