© 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. 97212
    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
    æĸ°å¼Ģ
    -0.28
    -hit
    -0.28
    å°¸
    -0.25
    Intialized
    -0.25
    endas
    -0.25
    //{{
    -0.24
    rica
    -0.24
    -solid
    -0.24
    Decoration
    -0.24
    åĪ¸
    -0.24
    POSITIVE LOGITS
     heck
    0.29
    æī¾äºĨ
    0.25
    åĺ´
    0.24
    顧
    0.24
    KeyValuePair
    0.24
     immigr
    0.24
    躲
    0.24
    ãģ£ãģįãĤĬ
    0.23
     outr
    0.23
    æĬĬèĩªå·±çļĦ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.