© 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. 130284
    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
     masks
    -0.30
    MASK
    -0.29
     CreateTable
    -0.27
    åĬłçıŃ
    -0.26
     Masks
    -0.26
    phans
    -0.25
    ä¸Ŀ毫ä¸į
    -0.25
    çĨ¨
    -0.24
    çī¹æ´¾åijĺ
    -0.24
    -mask
    -0.24
    POSITIVE LOGITS
    Station
    0.28
    åľ°éĿ¢
    0.25
     out
    0.25
     predic
    0.25
    station
    0.25
    è¦ģèĢĥèĻij
    0.24
    åIJİéĿ¢
    0.24
     Arch
    0.24
    reb
    0.24
    éĻIJ度
    0.23
    Activations Density 12.106%

    No Known Activations

    This feature has no known activations.