© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51924
    Prev
    Next
    INDEX
    Explanations

    am, ide, osphoorus, ochlorine, anes

    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
    odata
    -0.07
    ability
    -0.06
     Stub
    -0.06
    ç½®ä¹ĭ
    -0.06
    å¤ļä½ĻçļĦ
    -0.06
    oby
    -0.06
    /default
    -0.06
     fiet
    -0.06
    .stub
    -0.06
    équ
    -0.06
    POSITIVE LOGITS
    ç±»åĴĮ
    0.14
    ç±»çŃī
    0.14
    ç±»
    0.13
    ä¸Ģç±»
    0.12
    ç±»çļĦ
    0.12
    两大类
    0.12
    两类
    0.11
    类产åĵģ
    0.10
    ä¸Ģæĸ°
    0.10
    çļĦä¸Ģç±»
    0.10
    Activations Density 0.350%

    No Known Activations