© 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. 10495
    Prev
    Next
    INDEX
    Explanations

    require '

    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
    ен
    -0.07
    å¾Ĺ罪
    -0.07
    åĽłæѤèĢĮ
    -0.06
    ÙĪÙĨ
    -0.06
    {}",
    -0.06
    ille
    -0.06
    æĬĢæľ¯çŃī
    -0.06
    chemas
    -0.06
    cek
    -0.06
    {}".
    -0.06
    POSITIVE LOGITS
    é»ĺ认æİĴåºı
    0.09
    oui
    0.08
    versa
    0.08
    建ç«Ļ
    0.08
    alda
    0.08
     nakna
    0.08
    nock
    0.08
    Æ¡i
    0.08
     Conspiracy
    0.08
     angk
    0.08
    Activations Density 0.002%

    No Known Activations