© 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. 20-TRANSCODER-HP
    7. 62697
    Prev
    Next
    INDEX
    Explanations

    in/into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     xuyên
    -0.31
    kea
    -0.28
    çĽį
    -0.26
    RAIN
    -0.26
    诱åıij
    -0.25
    trä
    -0.25
    SETS
    -0.24
    <l
    -0.24
    eri
    -0.24
    WAY
    -0.24
    POSITIVE LOGITS
    çĥĤ
    0.28
    linux
    0.26
     cutoff
    0.25
     cut
    0.25
    æºĥ
    0.24
    Pet
    0.24
    _linux
    0.24
    Linux
    0.24
    并
    0.24
    æĪª
    0.24
    Activations Density 11.814%

    No Known Activations