© 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. 64873
    Prev
    Next
    INDEX
    Explanations

    Code and random data

    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
    uan
    -0.27
     Chain
    -0.24
    vic
    -0.24
    keley
    -0.24
    www
    -0.24
     Association
    -0.24
    .chain
    -0.23
    çĶ¥
    -0.23
    itet
    -0.23
     www
    -0.23
    POSITIVE LOGITS
    äºij端
    0.27
    ARIO
    0.27
    orate
    0.25
    åħ¨è¿ĩç¨ĭ
    0.25
     conv
    0.25
    weep
    0.25
    æ¯Ķè¾ĥé«ĺ
    0.25
    üst
    0.24
    atorial
    0.24
    perature
    0.24
    Activations Density 0.530%

    No Known Activations