© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    structure, red, PT, sensor, length

    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
    hiba
    -0.07
    asks
    -0.07
    çĬĢåĪ©
    -0.07
    æĸ°æŃĮ
    -0.07
    æľĢçµĤ
    -0.07
    asons
    -0.07
    леÑģ
    -0.07
    缤纷
    -0.06
     /(
    -0.06
    ỡ
    -0.06
    POSITIVE LOGITS
    dung
    0.08
    eg
    0.07
    åı¦ä¸Ģæĸ¹éĿ¢
    0.07
    ãģ«åĬłãģĪ
    0.07
    endem
    0.07
    uddy
    0.07
    ×Ļ×ĵ
    0.07
    vus
    0.07
    lp
    0.06
    kanz
    0.06
    Activations Density 0.190%

    No Known Activations