© 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. 64018
    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
    acher
    -0.30
    ä»Ģ
    -0.26
    åıĪ被
    -0.25
    inally
    -0.25
    伺
    -0.24
    etty
    -0.24
    æĿIJæĸĻ
    -0.24
    çĶĺ
    -0.24
    styl
    -0.24
    doctype
    -0.24
    POSITIVE LOGITS
    ÃľN
    0.28
    -bed
    0.27
    unding
    0.24
     dissoci
    0.23
    ãģ«ãģĬ
    0.23
    çļĦæĿĥåĪ©
    0.23
     routines
    0.23
    çļĦèµĦéĩij
    0.23
     EXCEPTION
    0.22
    åĦ¿
    0.22
    Activations Density 3.510%

    No Known Activations

    This feature has no known activations.