© 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. 30-TRANSCODER-HP
    7. 97118
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç±³å°Ķ
    -0.29
    èĪªè¿IJ
    -0.28
    lett
    -0.27
     Sadd
    -0.27
    mons
    -0.26
    èĤºçĻĮ
    -0.26
    oui
    -0.24
    æĮ¥
    -0.23
     Redistribution
    -0.23
    åĩºåİ»
    -0.23
    POSITIVE LOGITS
    顺
    0.31
    ForKey
    0.27
     maturity
    0.26
    .keras
    0.25
    ä¼ĺåħĪ
    0.25
    æĬ¼
    0.25
    æĺİå¹´
    0.24
     Lumia
    0.24
    ä»»
    0.23
    ä¸Ģåı£æ°Ķ
    0.23
    Activations Density 0.149%

    No Known Activations

    This feature has no known activations.