© 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. 20115
    Prev
    Next
    INDEX
    Explanations

    block, inhibition, medical terms

    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
    opers
    -0.07
    åı£åŃIJ
    -0.07
    éĶIJæĦı
    -0.07
    为åģļ好
    -0.07
    æŀģéĢŁ
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    Ñĥг
    -0.06
    รวà¸ĩ
    -0.06
    rido
    -0.06
    anser
    -0.06
    POSITIVE LOGITS
    对åħ¶ä»ĸ
    0.20
    å½¼æѤçļĦ
    0.18
    äºĴ缸
    0.17
    缸äºĴ
    0.16
    å½¼æѤ
    0.16
     sesama
    0.14
     дÑĢÑĥг
    0.13
    åĪ°åħ¶ä»ĸ
    0.13
     mutual
    0.13
    äºĴ为
    0.12
    Activations Density 0.391%

    No Known Activations