© 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. 129044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    erus
    -0.29
     illustrations
    -0.26
     particular
    -0.26
    ModelState
    -0.26
    .Sdk
    -0.25
    aven
    -0.25
     illustration
    -0.25
    stantiate
    -0.25
    Century
    -0.24
    è¶Ĭ
    -0.24
    POSITIVE LOGITS
    å±ij
    0.28
    注æĦıåĪ°
    0.26
    ween
    0.26
    èı½
    0.25
    ä½łæĥ³
    0.24
    岩
    0.24
    /Private
    0.24
     CWE
    0.24
    BS
    0.23
    ãĤį
    0.23
    Activations Density 14.752%

    No Known Activations

    This feature has no known activations.