© 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. 21493
    Prev
    Next
    INDEX
    Explanations

    security policy or scandal

    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
    åħ¨éĥ¨è¯Ħ论
    -0.08
     ÎŃγι
    -0.08
    ergia
    -0.07
    ifico
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    ä¸įå¿ĺ
    -0.07
    å°ıå¹³
    -0.07
    ilage
    -0.07
    crast
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
    POSITIVE LOGITS
    asaran
    0.06
     اÙĦÙħÙĩ
    0.06
    lop
    0.06
    ossi
    0.06
     sue
    0.06
    orphic
    0.05
    nict
    0.05
     Pent
    0.05
     enthus
    0.05
    鼷æĸ¯
    0.05
    Activations Density 0.823%

    No Known Activations