© 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. 56424
    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
    ariat
    -0.30
    FLOW
    -0.27
     Section
    -0.26
    rary
    -0.26
    ournals
    -0.26
    aru
    -0.26
     flow
    -0.25
     Cement
    -0.25
    æµģåĬ¨
    -0.25
    .lp
    -0.24
    POSITIVE LOGITS
    chez
    0.29
    TabIndex
    0.28
     rooting
    0.27
     analyzes
    0.27
     embr
    0.25
    antha
    0.25
     hydr
    0.24
    ighthouse
    0.24
    çļĦçIJĨæĥ³
    0.24
    طة
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.