© 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. 14-TRANSCODER-HP
    7. 39495
    Prev
    Next
    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Cran
    -0.26
    æIJ¬å®¶
    -0.25
    CollectionView
    -0.24
     wartime
    -0.24
    asta
    -0.24
     Vish
    -0.24
     backlog
    -0.24
    å¼±
    -0.24
    ighest
    -0.24
     expos
    -0.23
    POSITIVE LOGITS
    天èĬ±
    0.31
    åIJ¬å¾Ĺ
    0.28
    Accepted
    0.28
    æ¢Ń
    0.26
     Fancy
    0.26
    ä»Ģä¹Īåľ°æĸ¹
    0.26
    èİ·æĤī
    0.26
    éĹ»è¨Ģ
    0.25
    æľīè¿ĩ
    0.24
    çĶ¨æĪ·æıIJä¾Ľ
    0.24
    Activations Density 0.197%

    No Known Activations