© 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. 62862
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    cast
    -0.27
    AGIC
    -0.27
    IDD
    -0.25
     Ebony
    -0.25
    gnore
    -0.24
     tùy
    -0.24
     lạc
    -0.24
    ModelError
    -0.24
    ctrine
    -0.24
    planation
    -0.24
    POSITIVE LOGITS
    æĢĢ
    0.30
    ãĥIJãĤ¹
    0.27
    èĿĹ
    0.25
     supplementary
    0.25
    isz
    0.24
    ivec
    0.24
    uti
    0.24
    inema
    0.24
    综
    0.24
     partition
    0.24
    Activations Density 1.809%

    No Known Activations

    This feature has no known activations.