© 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. 63689
    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
     reinforcing
    -0.29
     reinforce
    -0.29
    acent
    -0.27
    ickers
    -0.27
    央
    -0.26
    çIJļ
    -0.26
    éªļ
    -0.26
     dense
    -0.25
     persistent
    -0.25
    稳
    -0.25
    POSITIVE LOGITS
    åī¯åİ¿éķ¿
    0.27
    alias
    0.26
    .spin
    0.26
    çŃ®
    0.25
    agenda
    0.25
    åĩ»
    0.25
    ice
    0.25
    æ¯Ķãģ¹
    0.24
    å·®è·Ŀ
    0.24
    å·®å¼Ĥ
    0.24
    Activations Density 18.433%

    No Known Activations

    This feature has no known activations.