© 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. 90211
    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
    EL
    -0.34
    OU
    -0.29
    atar
    -0.28
     NM
    -0.28
    ç³»ç»ŁçļĦ
    -0.28
    OC
    -0.27
    ATAR
    -0.27
    Ấ
    -0.26
    éĩĮçļĦ
    -0.26
     RC
    -0.26
    POSITIVE LOGITS
    èĻļå¼±
    0.29
     Subcommittee
    0.28
    åıijæī¬
    0.27
     fitte
    0.27
     médec
    0.26
    theless
    0.25
     ShoppingCart
    0.25
     Greenville
    0.24
    bestos
    0.24
    ToWorld
    0.24
    Activations Density 0.079%

    No Known Activations

    This feature has no known activations.