© 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. 90112
    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
    çļĦå½±åĵį
    -0.28
    imon
    -0.28
    æĿĸ
    -0.28
    itter
    -0.26
    æĢ§çļĦ
    -0.26
    éĩį
    -0.25
    hap
    -0.25
    CLOSE
    -0.25
     correct
    -0.25
    æľĢè¿ij
    -0.24
    POSITIVE LOGITS
    agate
    0.28
    rlen
    0.27
    segue
    0.26
    ä¸Ģè§Ī
    0.25
    åĬĪ
    0.25
    è§ĨåIJ¬
    0.24
    yi
    0.24
    creen
    0.24
     rop
    0.23
    etting
    0.23
    Activations Density 2.578%

    No Known Activations

    This feature has no known activations.