© 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. 27-TRANSCODER-HP
    7. 7860
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ĥ¬
    -0.27
    imd
    -0.26
    pj
    -0.26
    utory
    -0.26
    (il
    -0.25
     moreover
    -0.25
    å¼¯æĽ²
    -0.24
    æľīæĽ´å¥½çļĦ
    -0.24
     robert
    -0.24
    ä¹Į
    -0.24
    POSITIVE LOGITS
     Reflect
    0.28
    -collapse
    0.28
    ittings
    0.27
     reflections
    0.25
    aby
    0.25
    åħ¨èĥ½
    0.24
     Priv
    0.24
     crédit
    0.24
    rap
    0.24
     Reflection
    0.23
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.