© 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. 20-TRANSCODER-HP
    7. 140639
    Prev
    Next
    INDEX
    Explanations

    programming code/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ido
    -0.26
    åīĤ
    -0.25
     themselves
    -0.25
    ä¸įäºĨ解
    -0.24
    伦çIJĨ
    -0.24
    áºŃy
    -0.23
    _possible
    -0.23
    ä¸į太
    -0.23
     NI
    -0.23
    [source
    -0.23
    POSITIVE LOGITS
    uba
    0.30
     Hum
    0.28
     Border
    0.25
     ÐijÑĢ
    0.25
     cursed
    0.24
     Glow
    0.24
     Infer
    0.24
     Bench
    0.24
     rounded
    0.23
     Meghan
    0.23
    Activations Density 12.521%

    No Known Activations