© 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. 129001
    Prev
    Next
    INDEX
    Explanations

    primates

    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
    ä¸İåIJ¦
    -0.27
    主人
    -0.26
     ster
    -0.25
    PEC
    -0.24
    alette
    -0.24
    issement
    -0.23
    sizeof
    -0.23
    peater
    -0.23
     suf
    -0.23
    ritel
    -0.23
    POSITIVE LOGITS
    åĿIJä¸ĭ
    0.26
    tracts
    0.26
    WEEN
    0.25
    åĵij
    0.25
    è°¤
    0.24
    =(-
    0.24
    æĬ¤çħ§
    0.24
    ÑĪед
    0.24
     CONSTANTS
    0.24
     rewritten
    0.23
    Activations Density 3.001%

    No Known Activations