© 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. 59996
    Prev
    Next
    INDEX
    Explanations

    children, childs, or successors

    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
    Negative Logits
    æł¸å¿ĥä»·åĢ¼
    -0.07
    ystack
    -0.07
    moire
    -0.07
    ä¸Ńå¿ĥå·¥ä½ľ
    -0.07
    stants
    -0.06
    å¦Īå¦Ī们
    -0.06
     زد
    -0.06
     Refuge
    -0.06
    кала
    -0.06
    fon
    -0.06
    POSITIVE LOGITS
    å·¦åı³
    0.08
    ambu
    0.08
    åı³ä¾§
    0.08
     successors
    0.07
     children
    0.07
    ovation
    0.07
    expand
    0.07
    /right
    0.07
    åŃIJ女
    0.07
    æī©å±ķ
    0.07
    Activations Density 0.020%

    No Known Activations