© 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. 113056
    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
    èĥª
    -0.27
    arness
    -0.27
     unions
    -0.26
    éĴ§
    -0.24
    HOUSE
    -0.24
    à§İ
    -0.24
     UN
    -0.24
     portions
    -0.24
    æľŃ
    -0.24
    ctions
    -0.23
    POSITIVE LOGITS
    rift
    0.26
    è¡Įä¸ļä¸Ń
    0.25
    shell
    0.24
    .Hit
    0.24
    èĩªåĬ©
    0.24
    å¼¹
    0.24
     vacancies
    0.24
     dust
    0.24
    çīµ
    0.23
    èĩªè§ī
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.