© 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. 33194
    Prev
    Next
    INDEX
    Explanations

    ; followed by context connector

    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¿Ļæł·ä¸Ģ个
    -0.08
    å½¢å¼ıå¤ļæł·çļĦ
    -0.07
    çĻ¾å·Ŀ
    -0.06
    ×ķת
    -0.06
    вален
    -0.06
    enuous
    -0.06
    aveur
    -0.06
    æĽ´æ²¡æľī
    -0.06
    åĩºä¸Ģ份
    -0.06
    åı¦å¤ĸä¸Ģ个
    -0.06
    POSITIVE LOGITS
    ayar
    0.09
    it
    0.08
    è°ĵä¹ĭ
    0.08
    İ
    0.08
     it
    0.07
    缮çļĦæĺ¯
    0.07
    endt
    0.07
     only
    0.07
    kit
    0.07
    ible
    0.07
    Activations Density 0.082%

    No Known Activations