© 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. 34062
    Prev
    Next
    INDEX
    Explanations

    reveal

    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
    inals
    -0.08
    codes
    -0.08
    ct
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    ucker
    -0.07
    undra
    -0.07
    acus
    -0.07
    ban
    -0.07
    ÑĥÑģ
    -0.07
    URATION
    -0.07
    POSITIVE LOGITS
    端åĢª
    0.14
    æĻ°
    0.10
    éļIJèĹıçļĦ
    0.09
    ä¸Ģæĸij
    0.09
     hidden
    0.09
     миÑĢÑĥ
    0.09
     adanya
    0.09
     bahwa
    0.09
     rÃłng
    0.08
    æĽ´å¤ļåħ³äºİ
    0.08
    Activations Density 0.087%

    No Known Activations