© 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. 30-TRANSCODER-HP
    7. 95052
    Prev
    Next
    INDEX
    Explanations

    citizen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    azole
    -0.29
    .outer
    -0.27
    ainter
    -0.26
    丧失
    -0.26
    é¢ł
    -0.26
    ium
    -0.26
    ä¸įåıĬ
    -0.26
    exter
    -0.25
    丢失
    -0.25
    丢äºĨ
    -0.25
    POSITIVE LOGITS
    cit
    0.42
    åħ¬æ°ij
    0.38
     citizens
    0.35
     citizen
    0.34
     citiz
    0.30
    well
    0.30
     citt
    0.30
     wholes
    0.29
     citizenship
    0.29
     living
    0.29
    Activations Density 0.885%

    No Known Activations