© 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. 30-TRANSCODER-HP
    7. 97043
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     flash
    -0.33
     pitch
    -0.28
     patch
    -0.28
     cancer
    -0.25
    swick
    -0.25
    pitch
    -0.25
    éĺı
    -0.25
    ç¼Ŀ
    -0.25
    åIJĬ
    -0.25
     Python
    -0.25
    POSITIVE LOGITS
    å¯Ĥ
    0.27
    åľ°è¯´
    0.26
    lectic
    0.26
    åģķ
    0.25
    åĪ»
    0.25
    rig
    0.25
     agre
    0.25
    éļĶ
    0.24
     continua
    0.24
    å¾·æĭī
    0.24
    Activations Density 0.004%

    No Known Activations