© 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. 140900
    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
    idel
    -0.28
    MESS
    -0.27
    ores
    -0.26
    åłĨæĶ¾
    -0.26
    åIJİ
    -0.25
    phet
    -0.25
    佶
    -0.25
    pNet
    -0.25
    -flex
    -0.24
    ulos
    -0.24
    POSITIVE LOGITS
    åį°
    0.28
    croft
    0.26
     richt
    0.26
     nomin
    0.26
     Counter
    0.25
    ridge
    0.25
     Combined
    0.24
     Introduced
    0.24
    cb
    0.24
     Indigenous
    0.24
    Activations Density 3.784%

    No Known Activations

    This feature has no known activations.