© 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. 18-TRANSCODER-HP
    7. 88098
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åı¦ä¸ĢåįĬ
    -0.27
    anmar
    -0.26
    oxy
    -0.26
    çĽ¸äº²
    -0.26
    imson
    -0.25
    sp
    -0.25
    禧
    -0.24
    icast
    -0.24
    çīĿ
    -0.24
    pps
    -0.24
    POSITIVE LOGITS
    综
    0.26
    ç²¾éĢī
    0.25
    综åIJĪ
    0.24
    å¼ķåħ¥
    0.24
     boto
    0.23
    å½¢åĬ¿
    0.23
    ή
    0.23
    社åĮº
    0.23
    iaz
    0.23
    firm
    0.23
    Activations Density 0.319%

    No Known Activations

    This feature has no known activations.