© 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. 130856
    Prev
    Next
    INDEX
    Explanations

    Possessive suffix

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /MPL
    -0.25
     }(
    -0.24
    ().'/
    -0.23
    pun
    -0.23
    .obj
    -0.23
    .EXIT
    -0.23
    (exit
    -0.22
    éĽĨ
    -0.22
     Contributor
    -0.22
     sprung
    -0.22
    POSITIVE LOGITS
    fram
    0.30
    ragen
    0.28
    bbie
    0.28
    enery
    0.26
    uart
    0.26
    é©·
    0.25
    彩票
    0.25
    åºĦ
    0.25
    åĪ¤æĸŃ
    0.24
    æł·çļĦ
    0.24
    Activations Density 11.906%

    No Known Activations