© 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. 22350
    Prev
    Next
    INDEX
    Explanations

    code analysis and building

    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
    è¦ģä¹Ī
    -0.08
    oya
    -0.07
    æĪij们è¿ĻäºĽ
    -0.07
     either
    -0.07
    iesa
    -0.07
     Either
    -0.07
     либо
    -0.06
    è¦ģæĿ¥
    -0.06
    ÙħاÙĨ
    -0.06
    æī¬èµ·
    -0.06
    POSITIVE LOGITS
     again
    0.10
     подÑĢобно
    0.10
    again
    0.10
    å®Įæķ´
    0.09
    ä¸¥æł¼æĮīçħ§
    0.09
     nochmals
    0.09
     оконÑĩаÑĤелÑĮно
    0.09
    å®Įæķ´åľ°
    0.09
    å®Įæķ´çīĪ
    0.09
     повÑĤоÑĢно
    0.09
    Activations Density 0.022%

    No Known Activations