© 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. 97127
    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
    оÑī
    -0.29
    罩
    -0.27
    Encoder
    -0.26
    ToDevice
    -0.26
    encoder
    -0.25
     Buff
    -0.25
    笼
    -0.25
    пан
    -0.24
     bun
    -0.24
     Kling
    -0.24
    POSITIVE LOGITS
    ter
    0.27
    ients
    0.27
     unders
    0.26
    nds
    0.26
    åIJĦä½į
    0.25
    æĢ»å±Ģ
    0.25
    å²ģ
    0.25
    æĻļ
    0.24
    æ°ļ
    0.24
    ysis
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.