© 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. 58622
    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
    pq
    -0.23
     restored
    -0.23
    iddle
    -0.23
    -seat
    -0.23
    è¾ĥ
    -0.22
    lights
    -0.22
    .compare
    -0.22
    Sat
    -0.22
    纳æĸ¯
    -0.22
    .BL
    -0.21
    POSITIVE LOGITS
    unsigned
    0.26
    ç»Ļ
    0.24
     agree
    0.24
     unsigned
    0.23
    (unsigned
    0.23
    ListGroup
    0.23
     transf
    0.22
     Affero
    0.22
    è¦ģä¸įè¦ģ
    0.22
     agreement
    0.22
    Activations Density 1.230%

    No Known Activations

    This feature has no known activations.