© 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. 9925
    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
    çĺª
    -0.28
    榨
    -0.27
    妪
    -0.27
    node
    -0.27
    ,No
    -0.26
    ело
    -0.26
    Nom
    -0.25
    çĭŃ
    -0.24
    æĭ§
    -0.24
    ç¼ĸ
    -0.24
    POSITIVE LOGITS
    æĶ¶æĭ¾
    0.26
    åł´åIJĪãģ¯
    0.26
    ä¸Ģå¹ķ
    0.26
    åł´åIJĪ
    0.25
    éĩijå±ŀ
    0.25
     kadar
    0.24
    ç£ģ
    0.24
    ä¸įå®Į
    0.23
     quantum
    0.23
    缮åīįå·²
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.