© 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. 108696
    Prev
    Next
    INDEX
    Explanations

    User input

    np_max-act · gemini-2.0-flash
    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
    pton
    -0.30
     dang
    -0.28
     medically
    -0.26
    -board
    -0.25
     swirl
    -0.25
    ↵				↵
    -0.25
     molec
    -0.24
    çŃ¾è®¢äºĨ
    -0.24
     clinically
    -0.24
    ↵                        ↵
    -0.24
    POSITIVE LOGITS
    ies
    0.28
    æł¹
    0.26
    Ñħи
    0.26
    aura
    0.25
    owa
    0.25
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.24
    æł¹åŁº
    0.24
     arsenal
    0.23
    èIJ½
    0.23
    @@
    0.23
    Activations Density 1.541%

    No Known Activations