© 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. 58267
    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
    Not in Any Lists

    No Comments

    Negative Logits
    箾
    -0.26
     LoggerFactory
    -0.26
     cert
    -0.25
    ä¿Ń
    -0.25
    示
    -0.24
    å²ĺ
    -0.24
    REMOTE
    -0.24
    æľīä¸Ģå®ļçļĦ
    -0.24
     <",
    -0.24
     OSX
    -0.23
    POSITIVE LOGITS
    å®ŀä½ĵ
    0.28
    åī§çĥĪ
    0.28
    åľºåIJĪ
    0.26
    åīĤéĩı
    0.26
    èĩ´åij½
    0.25
    婵
    0.25
    åı¦ä¸ĢåįĬ
    0.25
    çĽ
    0.24
    åĺī宾
    0.24
    æĬ¤åį«
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.