© 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. 51479
    Prev
    Next
    INDEX
    Explanations

    Public Static

    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
    åı¯æĺ¯ä¸Ģ
    -0.08
    tag
    -0.07
    ÅĽc
    -0.07
    "_
    -0.07
    ping
    -0.06
    ë§ŀ
    -0.06
    Requested
    -0.06
     richiam
    -0.06
    çľģèĢĥ
    -0.06
     trailed
    -0.06
    POSITIVE LOGITS
    erva
    0.08
    дÑĢа
    0.07
    irk
    0.07
    ç¹
    0.07
    åī
    0.07
    è´¡
    0.07
    Directories
    0.06
    isikan
    0.06
    éĵ¿
    0.06
    esub
    0.06
    Activations Density 0.035%

    No Known Activations