© 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. 28933
    Prev
    Next
    INDEX
    Explanations

    both

    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
     pula
    -0.08
    æīĢæľīè¿ĻäºĽ
    -0.08
     particular
    -0.08
     all
    -0.08
     otherwise
    -0.07
    åıĪä¸Ģ
    -0.07
    ãģĵãģĿ
    -0.07
    å¾Ģå¾Ģä¼ļ
    -0.07
    ith
    -0.07
     tất
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.12
     sides
    0.10
     gleicher
    0.09
     câte
    0.09
     одина
    0.08
     individually
    0.08
    yun
    0.08
    äºĨä¸Ģéģį
    0.08
     lados
    0.07
    ensively
    0.07
    Activations Density 0.101%

    No Known Activations