© 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. 28203
    Prev
    Next
    INDEX
    Explanations

    the followed by words

    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
    aglio
    -0.06
    å¼ģ
    -0.06
    quine
    -0.06
    å¾ĹäºĨ
    -0.06
    alized
    -0.06
    æĺ¯ä»Ģä¹Īæł·
    -0.06
    éĥ½å¸Ĥè¨Ģæĥħ
    -0.06
    imore
    -0.06
    åĽŀãĤĬ
    -0.06
    rowsable
    -0.06
    POSITIVE LOGITS
    اÙĦا
    0.07
    gol
    0.07
    ali
    0.07
    ç£Ĭ
    0.07
    å°ıåħĶ
    0.07
     latter
    0.07
    )))),
    0.07
    .tp
    0.06
    ipi
    0.06
    ani
    0.06
    Activations Density 0.537%

    No Known Activations