© 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. 64552
    Prev
    Next
    INDEX
    Explanations

    Danish publications

    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
    à±į
    -0.10
    wards
    -0.09
    te
    -0.09
    سÙĦÙĪب
    -0.09
    er
    -0.09
    ting
    -0.08
    ر
    -0.08
    onde
    -0.07
    ergestellt
    -0.07
    eln
    -0.07
    POSITIVE LOGITS
    jenigen
    0.16
    ings
    0.11
    ingly
    0.10
    amental
    0.10
    INGS
    0.09
    edList
    0.09
    RIES
    0.09
    à¹Ħร
    0.08
    ếu
    0.08
     vá»±ng
    0.08
    Activations Density 1.380%

    No Known Activations