© 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. 27-TRANSCODER-HP
    7. 56445
    Prev
    Next
    INDEX
    Explanations

    Planting seeds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    亮çĤ¹
    -0.27
     Tie
    -0.26
     Along
    -0.26
     coli
    -0.25
    çģ«çĦ°
    -0.25
    åĽ·
    -0.24
    æĸĵ
    -0.24
     Domino
    -0.24
    贯穿
    -0.24
    临
    -0.24
    POSITIVE LOGITS
     broadcast
    0.33
    broadcast
    0.29
    ายà¸Ļ
    0.28
     broadcasting
    0.28
     broadcasts
    0.28
    广æĴŃ
    0.28
    æĭĽ
    0.28
    ldre
    0.28
    olic
    0.27
    haft
    0.27
    Activations Density 0.001%

    No Known Activations