© 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. 56336
    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
    isible
    -0.30
    ä¸Ĭä¸ĭ
    -0.26
     downt
    -0.26
    æ¯ıä¸Ģ
    -0.26
    inte
    -0.25
     address
    -0.25
     Rt
    -0.24
     backpack
    -0.24
    utory
    -0.24
    .vol
    -0.24
    POSITIVE LOGITS
    again
    0.28
    è¾IJ
    0.27
    æ²Ľ
    0.27
     Junk
    0.26
    plate
    0.26
    俱ä¹IJ
    0.25
    åīįæīĢ
    0.25
     %.
    0.25
    ometry
    0.24
    PERT
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.