© 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. 97161
    Prev
    Next
    INDEX
    Explanations

    Code, math, and foreign languages

    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
     bright
    -0.66
     Bright
    -0.56
    Bright
    -0.50
    åħīæĺİ
    -0.47
    bright
    -0.47
     brighter
    -0.46
    æĺİ亮
    -0.46
    亮
    -0.42
    çģ¿çĥĤ
    -0.40
     brightness
    -0.39
    POSITIVE LOGITS
    åħ«å¹´
    0.28
    ong
    0.27
    á»ĵi
    0.26
    åľ¨è¿ĩ渡
    0.26
    éĽ£
    0.24
    eping
    0.24
     Kurd
    0.24
    rift
    0.24
    åįģåĽĽæĿ¡
    0.24
     Newtown
    0.24
    Activations Density 0.886%

    No Known Activations