© 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. 106879
    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
     abstract
    -0.27
     widely
    -0.27
     only
    -0.26
    ç¼Ģ
    -0.25
    ls
    -0.25
     convenient
    -0.24
     norms
    -0.24
     inter
    -0.24
    æ¤įæłij
    -0.24
     tightly
    -0.24
    POSITIVE LOGITS
    icken
    0.28
    ì§Ī
    0.27
    .assignment
    0.27
    Accessory
    0.26
    禺
    0.26
    å·¥ç¨ĭè´¨éĩı
    0.25
    è·»
    0.24
    ialized
    0.24
     partes
    0.24
    indx
    0.24
    Activations Density 1.545%

    No Known Activations

    This feature has no known activations.