© 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. 90302
    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
    rica
    -0.29
    жÑĥ
    -0.28
    ipur
    -0.26
    iom
    -0.26
     THANK
    -0.25
    ätz
    -0.24
     equ
    -0.24
     spit
    -0.24
    åĩĭ
    -0.24
    VERS
    -0.24
    POSITIVE LOGITS
    ãĤŀ
    0.27
    robe
    0.26
    pace
    0.25
     costs
    0.24
    ç¼ĿéļĻ
    0.24
    ybrid
    0.24
    å¼ĺæī¬
    0.23
     hmm
    0.23
    两类
    0.23
    èĢĻ
    0.23
    Activations Density 0.914%

    No Known Activations

    This feature has no known activations.