© 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. 90171
    Prev
    Next
    INDEX
    Explanations

    Medical discharge/charge

    np_max-act · gemini-2.0-flash
    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
    åįĥéĩĮ
    -0.27
     Carp
    -0.27
    åĪĥ
    -0.26
     Kirst
    -0.25
    çĽ¸æľº
    -0.25
     Coil
    -0.24
    athing
    -0.24
     Inf
    -0.24
    Leod
    -0.24
    åħĭæĸ¯
    -0.24
    POSITIVE LOGITS
    itty
    0.27
     spare
    0.25
    cl
    0.25
    ãĪľ
    0.25
     UNITED
    0.25
     Yates
    0.25
    èĢĮå·²
    0.24
    SPARENT
    0.24
    lund
    0.23
     hanging
    0.23
    Activations Density 7.377%

    No Known Activations