© 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. 54918
    Prev
    Next
    INDEX
    Explanations

    macro definitions

    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
    说好
    -0.07
    bery
    -0.07
    åįĹå®ī
    -0.07
    ($('
    -0.06
    ãģĭãģĦ
    -0.06
    å¤©çľ¼
    -0.06
     varsa
    -0.06
    jeno
    -0.06
    ollen
    -0.06
    ment
    -0.06
    POSITIVE LOGITS
    opa
    0.07
        ↵↵↵
    0.07
    itar
    0.06
    erar
    0.06
    lk
    0.06
    моÑĤ
    0.06
    åij³
    0.06
    itore
    0.06
     Pou
    0.06
    ниÑĨ
    0.06
    Activations Density 0.124%

    No Known Activations