© 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. 19951
    Prev
    Next
    INDEX
    Explanations

    Character encoding and web standards

    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
    quarter
    -0.29
    磰
    -0.29
    æĽ²çº¿
    -0.28
    æŃĮ
    -0.28
    ukan
    -0.26
    ProgressHUD
    -0.26
    baum
    -0.25
    èĥ«
    -0.25
    rias
    -0.25
    åķĥ
    -0.24
    POSITIVE LOGITS
     iso
    0.37
    iso
    0.34
    .iso
    0.33
     AA
    0.31
     ISO
    0.30
    _iso
    0.29
    .lu
    0.29
    apons
    0.29
    apon
    0.29
    antee
    0.29
    Activations Density 14.983%

    No Known Activations