© 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. 30863
    Prev
    Next
    INDEX
    Explanations

    history, education, America, time, life, age

    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
    æĪĸéĥ¨åĪĨ
    -0.08
    ей
    -0.07
    allah
    -0.07
    memberof
    -0.07
    çŃīåľ¨
    -0.07
    oyer
    -0.07
    æĿ¥èĩª
    -0.07
    GRE
    -0.07
    æĽ´ä½³
    -0.06
    alah
    -0.06
    POSITIVE LOGITS
     überhaupt
    0.07
    èĭ¦è¾£
    0.07
    cimento
    0.07
    à¸ľà¹Īาà¸Ļà¸ģาร
    0.07
    èİ«è¿ĩäºİ
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    —from
    0.07
    ouw
    0.07
    által
    0.07
    究竣æĺ¯ä»Ģä¹Ī
    0.07
    Activations Density 0.290%

    No Known Activations