© 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. 90148
    Prev
    Next
    INDEX
    Explanations

    training and education

    np_max-act · gemini-2.0-flash
    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
    çıĻ
    -0.27
    è½²
    -0.25
    ModelError
    -0.25
    çĶŁæĦı
    -0.25
    çĵ¶åŃIJ
    -0.25
    bic
    -0.24
    itzer
    -0.24
    åı¦ä¸ĢåįĬ
    -0.24
     demanded
    -0.24
    /lic
    -0.24
    POSITIVE LOGITS
    idas
    0.27
    -colored
    0.27
    Lt
    0.26
    çĹķ迹
    0.26
    rug
    0.25
    iro
    0.25
    é©´
    0.24
    IRO
    0.24
    (opts
    0.24
    .contract
    0.24
    Activations Density 12.634%

    No Known Activations