© 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. 31-TRANSCODER-HP
    7. 18687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĴĻ
    -0.32
     Ashton
    -0.28
    .fill
    -0.27
    æĦĽ
    -0.26
    ertools
    -0.26
    软
    -0.26
    ä¿Ŀ
    -0.26
    åıĤ
    -0.26
    åĬ¡
    -0.25
    èĤī
    -0.25
    POSITIVE LOGITS
     Schwartz
    0.27
    รà¸ģ
    0.26
    -divider
    0.26
    uids
    0.26
    aby
    0.25
     :'
    0.24
    ipeg
    0.23
    æīĵæī°
    0.23
    åı£æ°´
    0.23
    èľ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.