© 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. 106882
    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
    ä½ĵ
    -0.28
    å®ŀéªĮ
    -0.27
    اء
    -0.25
    edm
    -0.25
    Ỽt
    -0.24
    quat
    -0.24
    elite
    -0.24
     Rev
    -0.24
    <Select
    -0.24
     back
    -0.23
    POSITIVE LOGITS
    驶
    0.25
     Principle
    0.25
    麼
    0.24
    çİĩ为
    0.24
    éķ¿è¿ľ
    0.24
    elper
    0.24
    车ä¸Ĭ
    0.23
     proced
    0.23
    åķĸ
    0.23
    marshal
    0.23
    Activations Density 66.794%

    No Known Activations

    This feature has no known activations.