© 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. 88356
    Prev
    Next
    INDEX
    Explanations

    unit measurements

    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
    inges
    -0.29
    缣
    -0.28
    avia
    -0.28
    \")
    -0.27
    .centerY
    -0.26
    è¿ijè§Ĩ
    -0.26
    æľīèī²
    -0.26
     çĽ
    -0.25
    çĽ
    -0.25
    使
    -0.25
    POSITIVE LOGITS
     Freeze
    0.27
    lists
    0.25
    atab
    0.25
    æĬĬè¿Ļ个
    0.25
    paren
    0.24
    éĹ
    0.24
    é¾Ħ
    0.23
    éĺij
    0.23
    tractor
    0.23
     Injury
    0.23
    Activations Density 9.964%

    No Known Activations