© 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. 58492
    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
     rewind
    -0.27
    ä½łè¦ģ
    -0.26
    orate
    -0.25
    èijº
    -0.25
     accuses
    -0.25
    solid
    -0.25
    åĶĨ
    -0.24
     Dates
    -0.24
    posites
    -0.24
    年以æĿ¥
    -0.24
    POSITIVE LOGITS
    QUAL
    0.28
     Mob
    0.28
     mob
    0.28
    mob
    0.27
    hole
    0.26
    erior
    0.25
    ær
    0.25
    Resolution
    0.25
    ä¸Ģä½ĵ
    0.25
    Ø·ÙĨ
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.