© 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. 129115
    Prev
    Next
    INDEX
    Explanations

    color

    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
    害
    -0.28
    urat
    -0.27
    anders
    -0.26
    ä¹ĭéģĵ
    -0.26
    -browser
    -0.25
     Dam
    -0.25
     ObjectOutputStream
    -0.25
    eworld
    -0.25
    imes
    -0.24
    _pieces
    -0.24
    POSITIVE LOGITS
    aily
    0.28
    ALE
    0.27
    all
    0.27
    éĽªèĬ±
    0.27
     flag
    0.25
    Flag
    0.23
    ала
    0.23
    SZ
    0.23
    ALLE
    0.23
    鼷
    0.23
    Activations Density 2.847%

    No Known Activations