© 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. 62606
    Prev
    Next
    INDEX
    Explanations

    particle physics experiments

    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
    /***
    -0.25
     Valent
    -0.25
    olo
    -0.24
    åĪĴ
    -0.24
    ptune
    -0.23
    ekyll
    -0.23
    èĤ²
    -0.23
    çĢĽ
    -0.23
    æĹłåģ¿
    -0.23
    ç¿®
    -0.23
    POSITIVE LOGITS
    nton
    0.28
    åı¸
    0.26
    uced
    0.26
    éļıçĿĢ
    0.25
    "]}
    0.25
     bulk
    0.24
    csr
    0.24
    æĿijéķĩ
    0.24
    HERE
    0.23
    uite
    0.23
    Activations Density 6.690%

    No Known Activations