© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129384
    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
    )size
    -0.28
    åłĩ
    -0.25
    çĽĴ
    -0.24
    illin
    -0.24
    ullo
    -0.24
    åģļå·¥
    -0.24
    :size
    -0.24
    cps
    -0.23
    (encoding
    -0.23
    ould
    -0.23
    POSITIVE LOGITS
    tracted
    0.28
     Perspective
    0.27
    å¼ł
    0.25
    å®ŀåľ¨
    0.25
     perspective
    0.25
    itor
    0.25
    ken
    0.24
    pered
    0.24
     ess
    0.24
    个å¤ļ
    0.24
    Activations Density 57.064%

    No Known Activations

    This feature has no known activations.