© 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. 32-TRANSCODER-HP
    7. 40973
    Prev
    Next
    INDEX
    Explanations

    El Salvador and Honduras

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ิà¸ķ
    -0.25
    æijĦ
    -0.25
    (geometry
    -0.25
    æij©
    -0.24
    åĨ³
    -0.24
    Cop
    -0.24
    åĩłä½ķ
    -0.24
    à´·
    -0.24
    CTION
    -0.24
     tongues
    -0.24
    POSITIVE LOGITS
     marg
    0.31
    å°ķ
    0.30
    kers
    0.28
    _sink
    0.27
    spiracy
    0.25
    ä¸įåĩĨ
    0.25
    庫
    0.24
    sea
    0.24
     Society
    0.24
     dro
    0.24
    Activations Density 0.003%

    No Known Activations