© 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. 18-TRANSCODER-HP
    7. 88258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     inf
    -0.30
    JB
    -0.28
    é©»
    -0.27
    tr
    -0.27
     top
    -0.26
    æ±ŁåĮĹ
    -0.26
     likely
    -0.26
     sense
    -0.26
    导åħ¥
    -0.25
     intern
    -0.25
    POSITIVE LOGITS
    å¸ģ
    0.33
    å¹£
    0.28
    acemark
    0.28
    ãģĨãģĵãģ¨
    0.27
    éĻªä½ł
    0.27
     Elli
    0.26
    obby
    0.26
    verter
    0.26
    ught
    0.25
     Alerts
    0.25
    Activations Density 3.002%

    No Known Activations

    This feature has no known activations.