© 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. 33-TRANSCODER-HP
    7. 52756
    Prev
    Next
    INDEX
    Explanations

    international companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ju
    -0.29
    king
    -0.27
    æ±Łä¸ľ
    -0.27
    åľ°
    -0.26
     kings
    -0.26
     mined
    -0.25
     king
    -0.25
     fi
    -0.25
    è¾Ļ
    -0.24
    æijĺ
    -0.24
    POSITIVE LOGITS
    YRO
    0.27
     Samar
    0.25
     Gir
    0.25
     Sty
    0.25
    mnt
    0.25
    abilia
    0.25
    abit
    0.25
    ahn
    0.24
    lients
    0.24
    åĩºéģĵ
    0.24
    Activations Density 0.014%

    No Known Activations