© 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. 30-TRANSCODER-HP
    7. 97143
    Prev
    Next
    INDEX
    Explanations

    database host names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     connected
    -0.50
     Connected
    -0.49
    è¿ŀæİ¥
    -0.47
    connected
    -0.45
     connect
    -0.43
    Connected
    -0.43
    CONN
    -0.42
    connect
    -0.42
     connection
    -0.41
     Connection
    -0.41
    POSITIVE LOGITS
    host
    0.27
    æĪĺæĸĹ
    0.26
    /host
    0.25
    root
    0.25
    hosts
    0.24
    wap
    0.24
    estic
    0.24
     Mazda
    0.24
    Marvel
    0.24
     StringComparison
    0.23
    Activations Density 0.148%

    No Known Activations