© 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. 23-TRANSCODER-HP
    7. 23370
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĪIJ为ä¸ŃåĽ½
    -0.33
    æīĢ产çĶŁçļĦ
    -0.29
    è¿Ļå¼ł
    -0.28
    åĩ¡æľ¬ç½ij
    -0.28
    æĸ©èİ·
    -0.26
    ^K
    -0.26
    Çİ
    -0.26
    è¿Ļ件
    -0.25
    è¿Ļé¦ĸ
    -0.25
    硬度
    -0.25
    POSITIVE LOGITS
    å¼ĢéŨ
    0.30
    ator
    0.30
    ators
    0.26
    (Resource
    0.26
    éĩij
    0.26
    ä¼ĺ
    0.26
    å¤ļ
    0.25
    IZER
    0.25
    ivol
    0.25
    cciones
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.