© 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. 18820
    Prev
    Next
    INDEX
    Explanations

    nuclear fuel and fissile material

    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
    彤
    -0.08
    èģĺ
    -0.08
    ä¸Ģå¸Ĩ
    -0.07
    OUCH
    -0.07
     respi
    -0.07
    åĩ°
    -0.07
    ä¸įä¼ļå½±åĵį
    -0.07
    alisme
    -0.07
    湧
    -0.07
     bib
    -0.07
    POSITIVE LOGITS
     concentration
    0.08
    orium
    0.08
     fiss
    0.08
    纯度
    0.08
    IPP
    0.07
    çīĮåı·
    0.07
    urgia
    0.07
    çĩĥæĸĻ
    0.07
    åĪ¶æĪIJçļĦ
    0.07
    åĤ¨éĩı
    0.07
    Activations Density 0.004%

    No Known Activations