© 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. 128975
    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
    幡
    -0.26
     Sadd
    -0.25
     bam
    -0.24
    AUSE
    -0.24
    é²ľ
    -0.24
    缯
    -0.24
    inent
    -0.23
    éķĪ
    -0.23
    åĬ©æĶ»
    -0.23
    çĿ¢
    -0.23
    POSITIVE LOGITS
     tableau
    0.27
    ordered
    0.26
    iant
    0.26
     FRONT
    0.26
    akest
    0.26
    èī¯
    0.26
     seq
    0.26
    ágina
    0.25
    Seq
    0.24
     æĸ¹
    0.24
    Activations Density 22.152%

    No Known Activations

    This feature has no known activations.