© 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. 16689
    Prev
    Next
    INDEX
    Explanations

    list items and technical terms

    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
    ourd
    -0.07
    å®Įåħ¨
    -0.07
    erval
    -0.07
    eza
    -0.06
    代
    -0.06
    ä¸ĩåı°
    -0.06
    常人
    -0.06
    abili
    -0.06
     Ùħص
    -0.06
    amisen
    -0.06
    POSITIVE LOGITS
    ugged
    0.08
    teks
    0.08
    NET
    0.07
    涯
    0.07
    wich
    0.07
    _UNIQUE
    0.07
    åłĤçļĦ
    0.07
    idis
    0.07
    heim
    0.07
     McL
    0.07
    Activations Density 0.698%

    No Known Activations