© 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. 90230
    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
     form
    -0.26
    eken
    -0.26
    eful
    -0.25
    å½¢å¼ı
    -0.25
     ",");↵
    -0.25
    æĪIJåĬŁçļĦ
    -0.25
     ajust
    -0.24
    edImage
    -0.24
    å½¢
    -0.24
    thora
    -0.24
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.27
    xm
    0.26
     statuses
    0.25
     quoting
    0.25
     meanings
    0.24
    _sms
    0.24
     quotation
    0.24
    wards
    0.23
    che
    0.23
    esis
    0.23
    Activations Density 13.803%

    No Known Activations

    This feature has no known activations.