© 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. 141351
    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
     base
    -0.27
     details
    -0.26
    åŁº
    -0.25
    ISA
    -0.25
     mana
    -0.25
    atown
    -0.25
    -base
    -0.24
     peak
    -0.24
     meng
    -0.24
    oard
    -0.23
    POSITIVE LOGITS
    ä¸¤å¼ł
    0.29
    æľŁåĨħ
    0.27
    (update
    0.27
    axed
    0.26
     uncomfort
    0.26
    åĽłåŃIJ
    0.26
    IMATE
    0.25
    @update
    0.25
    ogue
    0.25
    ä¼ļéķ¿
    0.25
    Activations Density 14.996%

    No Known Activations

    This feature has no known activations.