© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141356
    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
    Not in Any Lists

    No Comments

    Negative Logits
    è¶Ĭ好
    -0.29
    haul
    -0.28
    holes
    -0.28
    oub
    -0.26
     Guinea
    -0.26
    ãģ¡ãĤī
    -0.24
    ivy
    -0.24
    iaux
    -0.24
    å°¤
    -0.24
    尤为
    -0.24
    POSITIVE LOGITS
    è¿Ń
    0.30
    azzi
    0.26
     Dao
    0.26
    æŶéĹ´åĨħ
    0.24
     lagi
    0.24
     NOI
    0.23
    åij¨æľŁ
    0.23
    -handle
    0.23
    æķ´
    0.23
     Pont
    0.23
    Activations Density 9.699%

    No Known Activations

    This feature has no known activations.