© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11943
    Prev
    Next
    INDEX
    Explanations

    French, HTML, FTP, Guy

    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
    ERNEL
    -0.07
     âĢ¦
    -0.07
    åıijçİ°åľ¨
    -0.07
    [âĢ¦]
    -0.06
    .author
    -0.06
     verh
    -0.06
    aeda
    -0.06
    agraph
    -0.06
     Schiff
    -0.06
    idl
    -0.06
    POSITIVE LOGITS
    orent
    0.08
    empre
    0.07
    TY
    0.07
    ìĿ´ìĬ¤
    0.07
    æĤ²æ¬¢
    0.07
    bö
    0.07
    saus
    0.07
    ÙIJÙĬÙİ
    0.07
    θÏħ
    0.07
    ayar
    0.07
    Activations Density 0.023%

    No Known Activations