© 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. 129707
    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
    åħĭ
    -0.26
    å²Ĺ
    -0.25
    ãĥ¼ãĥł
    -0.25
    tsy
    -0.24
    stock
    -0.24
    妾
    -0.23
    sthrough
    -0.23
    starter
    -0.23
    ertility
    -0.23
    ypad
    -0.23
    POSITIVE LOGITS
    yms
    0.27
    xab
    0.26
    der
    0.26
    dong
    0.25
    ermal
    0.24
    JsonValue
    0.24
     trÆ°ng
    0.24
    æĢ§åij½
    0.24
    设计æĸ¹æ¡Ī
    0.24
    èµĦæĸĻæĺ¾ç¤º
    0.24
    Activations Density 0.466%

    No Known Activations

    This feature has no known activations.