© 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. 14-TRANSCODER-HP
    7. 41499
    Prev
    Next
    INDEX
    Explanations

    Pushing boundaries or limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ñħи
    -0.28
    oria
    -0.26
    arian
    -0.26
    ama
    -0.26
     positional
    -0.26
    ãģ°ãģĭãĤĬ
    -0.25
    家ä½ı
    -0.24
     Bik
    -0.24
     Likewise
    -0.24
     chances
    -0.24
    POSITIVE LOGITS
    èĭįçĻ½
    0.27
    èľĥ
    0.25
    ç¨ļ
    0.24
    骷
    0.24
    æīĭéĩĮ
    0.24
     existe
    0.24
     continu
    0.24
    [result
    0.24
    -ar
    0.23
    åıĮæīĭ
    0.23
    Activations Density 0.293%

    No Known Activations