© 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. 22-TRANSCODER-HP
    7. 99067
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    äºĭä¸ļåıijå±ķ
    -0.28
    erness
    -0.27
    ):\
    -0.25
    tlement
    -0.25
    ercul
    -0.24
    dens
    -0.24
    æļ
    -0.24
    æĸĩåĮĸ交æµģ
    -0.24
    %c
    -0.23
    .oc
    -0.23
    POSITIVE LOGITS
    ch
    0.29
    “
    0.27
    .setter
    0.26
    åĿ¡
    0.25
    jian
    0.25
    pect
    0.25
    egin
    0.23
     trá»Ŀi
    0.23
     wegen
    0.23
    ”↵
    0.23
    Activations Density 0.034%

    No Known Activations