© 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. 48683
    Prev
    Next
    INDEX
    Explanations

    construction of

    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
    atii
    -0.07
    åį¿
    -0.06
    LogLevel
    -0.06
    å¾Ĺä¸Ĭ
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
    èİ«åıĬ
    -0.06
    æĢİä¹Īå¤ĦçIJĨ
    -0.06
    ostal
    -0.06
    oord
    -0.06
     Bik
    -0.06
    POSITIVE LOGITS
    æĸ°ä¸Ģ
    0.08
    _from
    0.08
    hend
    0.08
    ä¸Ģ个æĸ°çļĦ
    0.08
    rama
    0.08
    FromFile
    0.08
    -from
    0.08
     ulang
    0.07
    FromString
    0.07
     daraus
    0.07
    Activations Density 0.023%

    No Known Activations