© 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. 18685
    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
    mdi
    -0.28
    æµģéĢļ
    -0.25
    xAF
    -0.25
    plotlib
    -0.25
    å®
    -0.25
    emax
    -0.25
     maxim
    -0.24
    ('/:
    -0.24
    /ws
    -0.24
     tackle
    -0.23
    POSITIVE LOGITS
    unda
    0.27
    bur
    0.27
    лив
    0.26
    _overlap
    0.26
    icast
    0.25
     hive
    0.24
    åķĸ
    0.24
    åī¯ç§ĺ书éķ¿
    0.24
    .Singleton
    0.24
     exception
    0.23
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.