© 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. 31-TRANSCODER-HP
    7. 17918
    Prev
    Next
    INDEX
    Explanations

    snippets of news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    apixel
    -0.29
    å¼Ģåı£
    -0.29
    gars
    -0.27
    åIJ¸éĻĦ
    -0.27
    rowave
    -0.24
    TX
    -0.24
    iks
    -0.24
    èı±
    -0.23
    äm
    -0.23
    gom
    -0.23
    POSITIVE LOGITS
    sticks
    0.28
    naire
    0.28
    esian
    0.26
    stick
    0.25
    iesz
    0.24
    ieten
    0.24
    便ä¼ļ
    0.24
    achen
    0.24
    便
    0.23
    former
    0.23
    Activations Density 34.710%

    No Known Activations