© 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. 64879
    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
     Burlington
    -0.27
    èķ¨
    -0.26
    бав
    -0.25
    æĺĨä»ij
    -0.25
     opposed
    -0.25
    erule
    -0.24
     adaptation
    -0.24
    ê¶Į
    -0.23
    MMMM
    -0.23
    ëĦ¤
    -0.23
    POSITIVE LOGITS
     programmes
    0.30
    ady
    0.28
    dy
    0.27
    常è¯Ĩ
    0.26
     rumours
    0.25
    ç»Łè®¡æķ°æį®
    0.25
    ioned
    0.25
    åĿIJ
    0.25
    ban
    0.24
     programme
    0.24
    Activations Density 4.906%

    No Known Activations

    This feature has no known activations.