© 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. 88106
    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
    éĻįä»·
    -0.26
    ossier
    -0.25
     drop
    -0.24
    Parsing
    -0.23
     Trace
    -0.23
     pg
    -0.23
     bis
    -0.23
     rede
    -0.23
    .Drop
    -0.23
    .proj
    -0.23
    POSITIVE LOGITS
    è¦ģç´§
    0.28
    è¶Ĭå¤ļ
    0.26
    èģŀ
    0.25
    unk
    0.25
    _each
    0.25
    çĤķ
    0.25
    ansion
    0.25
     ([]
    0.24
    isdiction
    0.24
    没è§ģè¿ĩ
    0.24
    Activations Density 2.888%

    No Known Activations

    This feature has no known activations.