© 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. 141588
    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
     IDR
    -0.28
    ADR
    -0.27
     AVR
    -0.27
    ä¸Ģä½į
    -0.24
    ç®Ĺ
    -0.24
     fists
    -0.23
    vue
    -0.23
    ç®ĹäºĨ
    -0.23
    ç½ijåıĭè¯Ħ论
    -0.23
    大æĪ·
    -0.23
    POSITIVE LOGITS
    ç¸
    0.30
    tie
    0.27
    Imp
    0.26
    é³Ĭ
    0.25
    .Imp
    0.24
    tex
    0.24
    ä¹ı
    0.24
     impl
    0.24
    èĨĽ
    0.23
    çİ°å®ŀ
    0.23
    Activations Density 4.732%

    No Known Activations

    This feature has no known activations.