© 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. 20-TRANSCODER-HP
    7. 140541
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    }@
    -0.30
    theless
    -0.26
     industry
    -0.26
    éĤ£äºĽ
    -0.25
    è¡Įä¸ļ
    -0.25
    è¡Įä¸ļçļĦ
    -0.25
     sector
    -0.25
    è¡Įä¸ļåįıä¼ļ
    -0.25
    ;↵↵↵↵↵
    -0.25
    è¡Įä¸ļåĨħ
    -0.25
    POSITIVE LOGITS
     fm
    0.30
    æłĩæĺİ
    0.27
    ä¸įè§ģ
    0.25
    emens
    0.24
    ãģĽãģ¦
    0.24
    addin
    0.24
    å®Įå¤ĩ
    0.24
    metros
    0.24
    |m
    0.24
    bury
    0.23
    Activations Density 5.140%

    No Known Activations

    This feature has no known activations.