© 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. 13648
    Prev
    Next
    INDEX
    Explanations

    assessment and risk detection

    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
    Õ¹
    -0.08
     INFORMA
    -0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.07
    entie
    -0.07
    onton
    -0.07
    详ç»ĨåĨħ容
    -0.07
    åħ¨åľº
    -0.07
     Viá»ħn
    -0.06
    ä»İä¸ļèµĦæł¼
    -0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.06
    POSITIVE LOGITS
    åį¦
    0.07
    çīĪ车åŀĭ
    0.07
    erto
    0.07
    å¾·éĩĮ
    0.07
    è¯Ĺåı¥
    0.07
    -io
    0.06
    vell
    0.06
    æĸ¹ç¨ĭå¼ı
    0.06
    æľīéģĵ
    0.06
    chutz
    0.06
    Activations Density 1.378%

    No Known Activations