© 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. 141100
    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
    utters
    -0.35
    书æĪ¿
    -0.27
    ffe
    -0.26
    ä¸įåľ¨ä¹İ
    -0.26
    xies
    -0.26
    traits
    -0.26
    .payload
    -0.26
     Swim
    -0.25
     Airways
    -0.25
     twilight
    -0.24
    POSITIVE LOGITS
    ÑĪе
    0.27
     ÑĤоÑĩ
    0.26
     Tele
    0.25
    azon
    0.25
    LOT
    0.25
    OTT
    0.25
    覽
    0.24
    çĸı
    0.24
    éĴ©
    0.24
     calor
    0.24
    Activations Density 54.904%

    No Known Activations

    This feature has no known activations.