© 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. 19-TRANSCODER-HP
    7. 9463
    Prev
    Next
    INDEX
    Explanations

    document beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    atters
    -0.28
    undra
    -0.27
    PRI
    -0.26
    çĦ¶æĺ¯
    -0.25
    ijľ
    -0.25
    ugal
    -0.25
    idable
    -0.25
     sod
    -0.25
    cede
    -0.25
    -addons
    -0.24
    POSITIVE LOGITS
     programm
    0.25
    èĩªèIJ¥
    0.23
    swiper
    0.23
     evolution
    0.23
     standardized
    0.22
     collapsed
    0.22
     floors
    0.22
    å°»
    0.22
     except
    0.22
    ây
    0.21
    Activations Density 0.031%

    No Known Activations