© 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. 17952
    Prev
    Next
    INDEX
    Explanations

    .h include files

    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
    lopedia
    -0.07
    leon
    -0.07
    tings
    -0.07
    çĽĺ
    -0.07
    _nil
    -0.07
    缸åħ³æݨèįIJ
    -0.07
     Satuan
    -0.07
    kau
    -0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.07
    çĽĺä¸Ń
    -0.06
    POSITIVE LOGITS
    ubber
    0.07
    骨çļĦ
    0.07
    arkan
    0.07
    è¦ģçļĦ
    0.07
    çŃĶ主
    0.07
    -webpack
    0.07
    .builder
    0.07
    umus
    0.06
    è¡¥åĬŀ
    0.06
    åij³çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations