© 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. 29137
    Prev
    Next
    INDEX
    Explanations

    show that

    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
    .mx
    -0.09
    ervi
    -0.08
    erner
    -0.08
    ysi
    -0.08
    otos
    -0.08
    åħ¬åı¸åħ¬åijĬ
    -0.08
    æ³¾
    -0.08
    issy
    -0.08
     Pearce
    -0.08
    çĮ¿
    -0.08
    POSITIVE LOGITS
    éģĩ
    0.06
    ä¸įä¼ij
    0.06
    beth
    0.06
    好å¤ļ
    0.06
    æīĢå¾Ĺ
    0.06
    åľ¨çº¿
    0.06
    à¸ģร
    0.06
    pedia
    0.05
    rong
    0.05
    ä¸Ģ个æĺŁæľŁ
    0.05
    Activations Density 0.002%

    No Known Activations