© 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. 88331
    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
    å¤Ļ
    -0.30
     calcul
    -0.27
    //'
    -0.27
    GM
    -0.26
     mornings
    -0.25
    éĩįåŀĭ
    -0.25
     bout
    -0.24
    *'
    -0.24
    astle
    -0.24
    ãģ»ãģĭ
    -0.24
    POSITIVE LOGITS
    ierce
    0.29
    comed
    0.28
     dispersion
    0.27
     Disp
    0.27
    æĭ¿
    0.27
    æķ£
    0.26
     WHATSOEVER
    0.25
     diá
    0.25
    离
    0.25
     Bare
    0.25
    Activations Density 0.942%

    No Known Activations

    This feature has no known activations.