© 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. 62759
    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
    符
    -0.26
    yang
    -0.25
    ses
    -0.25
     charg
    -0.25
    éģĹ
    -0.24
    kbd
    -0.24
    ç©°
    -0.24
     eigentlich
    -0.23
     UI
    -0.23
    åı¦ä¸Ģè¾¹
    -0.23
    POSITIVE LOGITS
    abal
    0.27
    ullen
    0.26
    irling
    0.26
    人åı£
    0.26
     cur
    0.25
    ARDS
    0.25
    .blit
    0.25
    opleft
    0.24
    éŀł
    0.24
    INGTON
    0.24
    Activations Density 20.850%

    No Known Activations

    This feature has no known activations.