© 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. 106931
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Rew
    -0.29
    -stop
    -0.26
    .Ap
    -0.26
    é¡·
    -0.25
    -light
    -0.24
     stop
    -0.24
     mute
    -0.24
    -gnu
    -0.24
     stump
    -0.24
    åħ³åģľ
    -0.24
    POSITIVE LOGITS
    çļĦç»ĵæŀľ
    0.26
    iox
    0.26
    éĶĢ
    0.25
    Ñīин
    0.24
     swear
    0.24
    opia
    0.24
    稼
    0.24
    кÑĢаÑĤ
    0.24
    osis
    0.23
    ejs
    0.23
    Activations Density 2.641%

    No Known Activations

    This feature has no known activations.