© 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. 90318
    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
     *(*
    -0.31
    icot
    -0.28
    enment
    -0.28
     useStyles
    -0.26
    ATAR
    -0.26
    vasion
    -0.24
    htub
    -0.24
     Lyons
    -0.24
    atar
    -0.24
    产
    -0.24
    POSITIVE LOGITS
     meaning
    0.27
    æĮ¥åıij
    0.27
     nothing
    0.25
     put
    0.25
    æİĺ
    0.25
    akis
    0.25
    åĩºè¡Ģ
    0.24
    æŀĦ
    0.24
    æİ¥è¿ij
    0.24
     perfectly
    0.24
    Activations Density 0.225%

    No Known Activations

    This feature has no known activations.