© 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. 62696
    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
    prepared
    -0.27
    ä¹ī
    -0.26
     ud
    -0.26
    çĤ¹è¯Ħ
    -0.26
     Floor
    -0.25
    UD
    -0.25
    èİ«
    -0.24
    åIJĥçļĦ
    -0.24
    alone
    -0.24
    çŁĽçĽ¾
    -0.24
    POSITIVE LOGITS
    ifr
    0.28
     *(*
    0.27
    uan
    0.25
    san
    0.24
    ovic
    0.23
    owitz
    0.23
     terminate
    0.23
     Tuấn
    0.23
     Spicer
    0.23
     Erect
    0.23
    Activations Density 8.097%

    No Known Activations

    This feature has no known activations.