© 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. 58388
    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
    为空
    -0.31
    oji
    -0.27
    éĺ´éĺ³
    -0.27
    çĽĸ
    -0.26
    lain
    -0.26
    AFE
    -0.26
    -memory
    -0.26
    ewire
    -0.25
    terr
    -0.25
    æł¸
    -0.25
    POSITIVE LOGITS
    elor
    0.29
    çĦ¶æĺ¯
    0.25
     band
    0.24
    æ¯ı个人çļĦ
    0.24
    累积
    0.24
     anybody
    0.24
    éĤ£è¾¹
    0.23
    è¿Ń
    0.23
    .destroyAllWindows
    0.23
    工夫
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.