© 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. 140713
    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
    çĶ»
    -0.26
    ayar
    -0.25
    å«©
    -0.24
    methodName
    -0.24
    REFERENCE
    -0.24
    èĥį
    -0.24
    ä¸Ģ个æĸ°çļĦ
    -0.24
    Weights
    -0.23
    rong
    -0.23
    arked
    -0.23
    POSITIVE LOGITS
    ERAL
    0.29
    ording
    0.29
    itespace
    0.27
    åĮº
    0.26
    otp
    0.26
    ä¸įèĥ½åĨį
    0.26
    oom
    0.25
    nel
    0.25
    ividual
    0.24
     Laud
    0.24
    Activations Density 10.796%

    No Known Activations

    This feature has no known activations.