© 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. 142578
    Prev
    Next
    INDEX
    Explanations

    research papers/studies

    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
    æī¿åĬŀ
    -0.29
    èĩ³æѤ
    -0.28
    -addons
    -0.27
     Äijến
    -0.27
    éĨļ
    -0.26
    ä»İä¸Ń
    -0.26
     Unable
    -0.25
    èĩ³
    -0.25
     inability
    -0.25
    æĦ§
    -0.24
    POSITIVE LOGITS
     compliance
    0.27
     complied
    0.27
     complying
    0.27
    .lift
    0.26
    mpp
    0.25
    lift
    0.25
     Compliance
    0.24
     integrated
    0.24
    æĹłåģ¿
    0.24
    hart
    0.24
    Activations Density 21.872%

    No Known Activations