© 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. 130081
    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
    joy
    -0.31
    ayan
    -0.28
    maxlength
    -0.28
    .rar
    -0.27
    æ¶īå«Į
    -0.27
    寨
    -0.26
    templ
    -0.25
     Labs
    -0.25
    _subscription
    -0.25
    arkan
    -0.25
    POSITIVE LOGITS
    cess
    0.27
    çĶ¨æĪ·çļĦ
    0.27
    人们çļĦ
    0.26
    ä¸ŃåĽ½çļĦ
    0.25
     population
    0.25
    kers
    0.24
    ç»İ
    0.24
     sort
    0.24
    丢
    0.23
    -clear
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.