© 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. 9926
    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
    çıį
    -0.28
    å°ijåIJĥ
    -0.26
    è¡Į为
    -0.26
    èµ°è¿Ľ
    -0.25
     volatility
    -0.25
    cano
    -0.25
    วา
    -0.24
     consumer
    -0.24
    DataProvider
    -0.24
    -s
    -0.24
    POSITIVE LOGITS
    mars
    0.28
    ä¹ĥæĺ¯
    0.28
     fellowship
    0.26
    å°ij女
    0.26
    older
    0.26
    Fil
    0.26
     +:+
    0.25
    Rec
    0.25
    aget
    0.25
    IDs
    0.25
    Activations Density 0.001%

    No Known Activations