© 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. 58494
    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
    quel
    -0.25
    é³ķ
    -0.25
    ATURE
    -0.24
    reat
    -0.24
    ä¸ŃåĽ½åĪ¶éĢł
    -0.24
    éĺµéĺµ
    -0.23
     dataSize
    -0.23
    ropping
    -0.23
    å·¥èīº
    -0.23
     doch
    -0.23
    POSITIVE LOGITS
    æ±ľ
    0.29
    Ranges
    0.28
    ç¼¢
    0.27
    å¹ķ
    0.27
    ä¸Ģæĸ¹
    0.27
    éĤ£ä¸Ģ
    0.26
    iswa
    0.26
    -earth
    0.26
    åī²
    0.26
    erset
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.