© 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. 32028
    Prev
    Next
    INDEX
    Explanations

    technical terms and classifications

    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
     Istitu
    -0.07
    ugd
    -0.07
    imps
    -0.07
    bord
    -0.07
    ä¸¤åľº
    -0.06
    éĽĨéķĩ
    -0.06
    atego
    -0.06
    สมุà¸Ĺร
    -0.06
    èĩªè§īæĢ§
    -0.06
    ELLE
    -0.06
    POSITIVE LOGITS
    /inc
    0.07
    iang
    0.07
    ogan
    0.07
    sock
    0.07
    iere
    0.06
    heim
    0.06
    urs
    0.06
    .Locale
    0.06
    æĻĵ
    0.06
     Ø´Ùĩ
    0.06
    Activations Density 0.772%

    No Known Activations