© 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. 130926
    Prev
    Next
    INDEX
    Explanations

    URLs and research

    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
    Negative Logits
     scratch
    -0.27
    iven
    -0.27
    éĹ®æĪij
    -0.26
    retty
    -0.25
    aviours
    -0.24
    енÑĮ
    -0.24
     verr
    -0.24
    _TMP
    -0.24
    /tool
    -0.24
    CHED
    -0.24
    POSITIVE LOGITS
     komm
    0.28
    oki
    0.24
    å¸Ŀ
    0.24
    )["
    0.24
    .drawText
    0.24
    developer
    0.23
    elight
    0.23
    lands
    0.23
    addWidget
    0.23
    êt
    0.23
    Activations Density 0.598%

    No Known Activations