© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    aviation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    亡
    -0.27
     car
    -0.26
    æĦıæĢĿ
    -0.26
     compositions
    -0.25
    åĨĴ
    -0.25
    åij¼åIJ¸
    -0.25
    fra
    -0.25
     prem
    -0.25
    .gms
    -0.24
     hom
    -0.24
    POSITIVE LOGITS
    èĪªå¤©
    0.53
     Aviation
    0.51
    èĪ°
    0.50
    é£ŀèĪ¹
    0.50
     aircraft
    0.50
     aviation
    0.49
    NASA
    0.49
     spacecraft
    0.48
    é£ŀæľº
    0.47
     Navy
    0.47
    Activations Density 0.070%

    No Known Activations