© 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. 90300
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    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
     reconcile
    -0.27
    ckt
    -0.24
     Constructs
    -0.24
     machine
    -0.24
    reation
    -0.24
    lia
    -0.23
    èħ´
    -0.23
     Parsons
    -0.23
    ering
    -0.23
     Builder
    -0.23
    POSITIVE LOGITS
    åĵĦ
    0.26
    à¸Ķา
    0.24
    讨
    0.24
    _flip
    0.24
    ç¿»
    0.24
    漫
    0.24
    Trim
    0.24
    KER
    0.24
     Hunt
    0.23
    åĩłç§į
    0.23
    Activations Density 4.698%

    No Known Activations