© 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. 63708
    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
    taskId
    -0.26
     phé
    -0.26
    ä¸Ģèµ·è£ħä¿®
    -0.23
    è¡£æŁľ
    -0.23
     decl
    -0.23
     probably
    -0.23
    aldo
    -0.23
     com
    -0.23
    .vaadin
    -0.23
    abel
    -0.23
    POSITIVE LOGITS
    RING
    0.30
    çħ§
    0.29
    licken
    0.27
     Aware
    0.27
    æłĩ
    0.27
     realised
    0.26
    -domain
    0.26
    åŁŁ
    0.25
     honoring
    0.25
     domains
    0.25
    Activations Density 3.640%

    No Known Activations

    This feature has no known activations.