© 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. 65286
    Prev
    Next
    INDEX
    Explanations

    others, each, pairs, next

    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
    äºĮèĢħ
    -0.09
    两èĢħ
    -0.07
     kedua
    -0.07
    è¿Ļæł·ä¸Ģ个
    -0.06
    å°±æĺ¯ä¸ª
    -0.06
    æĺ¯ä¸ª
    -0.06
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.06
    åıĪæĺ¯ä¸Ģ个
    -0.06
    formation
    -0.06
    orthand
    -0.06
    POSITIVE LOGITS
    ä¸Ģ个个
    0.15
    åIJĦèĩª
    0.14
    åIJĦèĩªçļĦ
    0.13
    约èĢĮåIJĮ
    0.12
     ones
    0.12
     themselves
    0.12
    éĻĨç»Ń
    0.11
    åIJĦæľī
    0.11
     jeweils
    0.11
    缸继
    0.11
    Activations Density 0.036%

    No Known Activations