© 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. 22-TRANSCODER-HP
    7. 86738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dise
    -0.28
     campaigns
    -0.27
     Framework
    -0.26
    áŀł
    -0.26
    ç«ĭæ³ķ
    -0.25
     frameworks
    -0.25
    دÙĩ
    -0.25
    åħ¨æ°ij
    -0.24
    /latest
    -0.24
    交æĺĵå¹³åı°
    -0.24
    POSITIVE LOGITS
    é¬ĥ
    0.28
    è¾Ī
    0.28
    侬
    0.27
    ä¿Ħ
    0.27
    è¿Ļ段
    0.26
     Pompe
    0.25
    IPS
    0.25
     Hä
    0.25
    ünst
    0.25
    æĺ¨æĹ¥
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.