© 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. 14-TRANSCODER-HP
    7. 39432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æīij
    -0.25
     stderr
    -0.25
    ixed
    -0.24
     planes
    -0.24
    å½¢
    -0.24
     quadrant
    -0.24
    Builders
    -0.24
    两边
    -0.24
    eeper
    -0.23
    acades
    -0.23
    POSITIVE LOGITS
    rou
    0.27
    jsc
    0.26
    sport
    0.26
    ->[
    0.25
    åį«
    0.25
    rogram
    0.25
     stal
    0.24
    oun
    0.24
    .ready
    0.24
    æĮ¯ãĤĬ
    0.24
    Activations Density 1.484%

    No Known Activations

    This feature has no known activations.