© 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. 18131
    Prev
    Next
    INDEX
    Explanations

    to write or include something

    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
    驼
    -0.07
    èĥ¸
    -0.07
    tractor
    -0.07
    å¥ļ
    -0.07
     Clair
    -0.07
    acio
    -0.06
    èĢ¸
    -0.06
    ë³Ħ
    -0.06
    å°¾éħĴ
    -0.06
     aura
    -0.06
    POSITIVE LOGITS
    ående
    0.08
    .main
    0.08
     möglichst
    0.07
    æĭīæĭī
    0.07
    imai
    0.07
    itty
    0.07
    å°½åı¯èĥ½
    0.07
     rewritten
    0.07
    åĽ°éļ¾çļĦ
    0.06
    åıĸå¾Ĺæĸ°
    0.06
    Activations Density 0.008%

    No Known Activations