© 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. 88779
    Prev
    Next
    INDEX
    Explanations

    technique

    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
    license
    -0.31
    -license
    -0.30
    åħ¸åŀĭ
    -0.26
    notated
    -0.26
    etty
    -0.24
    çIJĨæĥ³çļĦ
    -0.24
    installer
    -0.23
    serter
    -0.23
    esy
    -0.23
    游æĪıä¸Ń
    -0.23
    POSITIVE LOGITS
    å§Ķåijĺä¼ļ
    0.30
     emerging
    0.28
    .lin
    0.26
    endir
    0.25
     awake
    0.24
     hereby
    0.24
     steering
    0.24
    æĹ©æĻļ
    0.24
    ovy
    0.23
     group
    0.23
    Activations Density 0.273%

    No Known Activations