© 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. 142750
    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
    ularity
    -0.27
    urger
    -0.26
    åīįè¿°
    -0.26
    线æĿ¡
    -0.25
    ERE
    -0.24
     Bare
    -0.24
    ambi
    -0.24
    ccb
    -0.24
     resultant
    -0.23
    ধ
    -0.23
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.29
    带
    0.28
    oom
    0.27
    wit
    0.26
    ç¼ĵ
    0.26
    wat
    0.25
     доÑģÑĤ
    0.25
     singly
    0.24
    ä»Ģä¹ĪæŶåĢĻ
    0.24
     Iter
    0.24
    Activations Density 2.359%

    No Known Activations

    This feature has no known activations.