© 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. 42149
    Prev
    Next
    INDEX
    Explanations

    properties, group, ibility, enough, materials, able, gas, contrast

    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
    _TA
    -0.07
    ignon
    -0.07
    utions
    -0.07
    upas
    -0.07
    ĺ
    -0.07
    venge
    -0.07
    вки
    -0.07
    á»Ńng
    -0.07
    ловиÑĩ
    -0.07
    æ¯Ľæ¯Ľ
    -0.06
    POSITIVE LOGITS
    çī¹æĢ§çļĦ
    0.10
    -rich
    0.08
    æĿIJè´¨
    0.08
    çī¹æĢ§
    0.08
    å»ī
    0.08
    æĿIJè´¨çļĦ
    0.07
    æĿIJæĸĻçļĦ
    0.07
    rish
    0.07
     materials
    0.07
    æĿIJæĸĻ
    0.07
    Activations Density 0.089%

    No Known Activations