© 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. 142654
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    aspers
    -0.35
    ampo
    -0.27
    onium
    -0.26
    angen
    -0.26
    esy
    -0.26
    &r
    -0.26
    &q
    -0.26
    ä»Ģä¹Īåij¢
    -0.25
    perm
    -0.25
    åħĥå·¦åı³
    -0.25
    POSITIVE LOGITS
     pri
    0.27
    åı¦ä¸Ģ个
    0.26
     Intr
    0.25
     Routine
    0.24
     prior
    0.24
    doctype
    0.24
     terminal
    0.23
     bo
    0.23
     CAP
    0.23
     another
    0.23
    Activations Density 1.618%

    No Known Activations