© 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. 90242
    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
    eties
    -0.30
    æ±IJ
    -0.29
    驶
    -0.27
     vit
    -0.27
    åī¯ä¸»å¸Ń
    -0.27
    ndon
    -0.26
    imp
    -0.25
    åı£
    -0.24
    rid
    -0.24
    onom
    -0.24
    POSITIVE LOGITS
    [ID
    0.29
    责任ç¼ĸè¾ij
    0.26
    inan
    0.25
    esan
    0.24
     rav
    0.24
    _COMPAT
    0.23
     Aur
    0.23
    LBL
    0.23
    _LOGGER
    0.22
    åĨįåĪ°
    0.22
    Activations Density 34.903%

    No Known Activations

    This feature has no known activations.