© 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. 20846
    Prev
    Next
    INDEX
    Explanations

    Object.defineProperty

    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
    _LOC
    -0.09
     Obr
    -0.07
    çĭĤ
    -0.07
    asca
    -0.07
    æ³¢
    -0.07
    ASET
    -0.07
    panic
    -0.07
    åĽĽéĿ¢åħ«æĸ¹
    -0.07
    -windows
    -0.06
    èIJ¤
    -0.06
    POSITIVE LOGITS
    åı¸æ³ķåįıåĬ©
    0.07
    alba
    0.07
    atoria
    0.07
    asten
    0.07
    alette
    0.07
    elib
    0.07
    ارÙĬÙĨ
    0.07
    åijĢ
    0.06
    okus
    0.06
    ê¹Į
    0.06
    Activations Density 0.001%

    No Known Activations