© 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. 88103
    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
    åıĪæľī
    -0.28
    ç»ĻåĪ«äºº
    -0.27
    ylie
    -0.26
    psc
    -0.26
    пов
    -0.25
    ervers
    -0.25
    æļ®
    -0.25
    oser
    -0.25
    orm
    -0.24
     latitude
    -0.24
    POSITIVE LOGITS
    ::__
    0.28
    å¼Ģå±Ģ
    0.27
     }//
    0.26
    æµ·å²Ľ
    0.26
     hurt
    0.25
    äºĨä¸Ģåľº
    0.24
    pty
    0.24
    dcc
    0.24
    orp
    0.24
     Organisation
    0.24
    Activations Density 6.892%

    No Known Activations

    This feature has no known activations.