© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16095
    Prev
    Next
    INDEX
    Explanations

    IDs and numbers

    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
    u
    -0.07
    ara
    -0.06
     Battle
    -0.06
    年份
    -0.06
     Dual
    -0.06
    mma
    -0.06
    åıĮèħ¿
    -0.06
     hidro
    -0.06
    зиÑĢÑĥ
    -0.05
    éķ¿å¤§äºĨ
    -0.05
    POSITIVE LOGITS
    anio
    0.08
    éļĶ天
    0.08
     almoço
    0.08
     mismas
    0.08
    åħ¶ä¹IJ
    0.07
    à¹Ģà¸Ĺà¸Ļ
    0.07
    à¹ģà¸Ĺรà¸ģ
    0.07
    ULER
    0.07
    æķı
    0.07
     óc
    0.07
    Activations Density 0.077%

    No Known Activations