© 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. 113158
    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
    .crypto
    -0.26
    acci
    -0.25
    Pager
    -0.25
    è§Ĵ度
    -0.25
    ingers
    -0.24
     hunters
    -0.24
    inct
    -0.24
     sÄĥ
    -0.24
    æĬµ
    -0.23
    该åİ¿
    -0.23
    POSITIVE LOGITS
     Feinstein
    0.26
    med
    0.25
    æľīä¿¡å¿ĥ
    0.25
    å¼ĢèĬ±
    0.24
    讶
    0.24
    çĶ³
    0.24
    pile
    0.24
    产ä¸ļåįĩ级
    0.24
    èĬ±å¼Ģ
    0.23
    Original
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.