© 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. 62794
    Prev
    Next
    INDEX
    Explanations

    patents

    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
     afterward
    -0.30
    åijĬè¯ī她
    -0.28
    ç»Ļ她
    -0.28
     stos
    -0.25
    ChangeEvent
    -0.25
    ITCH
    -0.25
    çĶļèĩ³æĺ¯
    -0.25
    ä½Ĩ她
    -0.25
    avers
    -0.24
    让她
    -0.24
    POSITIVE LOGITS
    shi
    0.29
    ankan
    0.27
    .Microsoft
    0.25
    óg
    0.25
    å¥ķ
    0.24
    鹿
    0.24
    çĿĢæīĭ
    0.24
     pharmacies
    0.24
     ship
    0.23
     hooked
    0.23
    Activations Density 0.310%

    No Known Activations