© 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. 27-TRANSCODER-HP
    7. 58524
    Prev
    Next
    INDEX
    Explanations

    Proper Nouns/Titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .She
    -0.28
    æĬĬ她
    -0.27
    .INSTANCE
    -0.27
    å©¿
    -0.27
    lot
    -0.27
    ordon
    -0.27
    family
    -0.24
     ACCOUNT
    -0.24
    çªģåĩº
    -0.24
    emer
    -0.24
    POSITIVE LOGITS
    èĢģåĮĸ
    0.27
    æ³µ
    0.27
     Pump
    0.27
    -age
    0.26
    .paper
    0.26
    .liferay
    0.25
    欢è¿İæĤ¨
    0.25
    ç²³
    0.25
     older
    0.24
    $lang
    0.24
    Activations Density 0.003%

    No Known Activations