© 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. 142449
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    VML
    -0.33
    rms
    -0.31
    ERIC
    -0.29
    æĢİ
    -0.26
    ç¾ļ
    -0.25
     md
    -0.24
    ÃľN
    -0.24
     eclipse
    -0.24
    ILES
    -0.24
    å¤ļå°ij
    -0.24
    POSITIVE LOGITS
    land
    0.28
    rella
    0.25
    顾
    0.24
     adherence
    0.24
     ['$
    0.24
    åIJij举
    0.23
    çŀĮ
    0.23
     geli
    0.23
     hybrids
    0.23
    åIJij
    0.23
    Activations Density 3.834%

    No Known Activations