© 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. 43927
    Prev
    Next
    INDEX
    Explanations

    copyright notices and company names

    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
    ela
    -0.06
    奥å°Ķ
    -0.06
    dd
    -0.06
     T
    -0.06
    ли
    -0.06
    ä¸Ģé¡¿
    -0.06
    两个åŃĹ
    -0.06
    éĽĨåħ¨
    -0.06
    Âł
    -0.06
    å¤ĸåĬł
    -0.05
    POSITIVE LOGITS
    gnos
    0.08
    rong
    0.08
    æĹłæĤĶ
    0.08
    jure
    0.08
    urgia
    0.07
    ysis
    0.07
    -present
    0.07
    celet
    0.07
    ÙĴÙĥ
    0.07
    estas
    0.07
    Activations Density 1.255%

    No Known Activations