© 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. 7721
    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
     scient
    -0.27
    éĨĮ
    -0.26
    æľīåĬĽ
    -0.24
     fact
    -0.24
    ubber
    -0.24
    ven
    -0.24
    .CV
    -0.23
    æĪIJåĬŁä¸¾åĬŀ
    -0.23
     trains
    -0.23
    çĵ¶é¢Ī
    -0.23
    POSITIVE LOGITS
     Decomp
    0.27
     ENUM
    0.26
    alette
    0.26
    亮度
    0.26
     Rebel
    0.26
    immer
    0.25
    Õµ
    0.25
    -toggler
    0.25
    ruk
    0.25
    åĪĨ解
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.