© 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. 13161
    Prev
    Next
    INDEX
    Explanations

    days away

    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
    ushi
    -0.07
    noinspection
    -0.07
    ä¸ĥ大
    -0.06
    anzo
    -0.06
    uppy
    -0.06
     bro
    -0.06
    inds
    -0.06
    erien
    -0.06
    ç®ĹäºĨ
    -0.06
    çļĦåı¦ä¸Ģ
    -0.05
    POSITIVE LOGITS
    年建éĢł
    0.09
    etar
    0.08
    epy
    0.08
    æĥ¨æ·¡
    0.07
    _configure
    0.07
    irk
    0.07
    -await
    0.07
    itionally
    0.07
    antil
    0.07
     '{$
    0.07
    Activations Density 0.027%

    No Known Activations