© 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. 108122
    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
    å®īåħ¨ç®¡çIJĨ
    -0.27
    ther
    -0.26
    lius
    -0.25
     dismissing
    -0.25
    thers
    -0.25
    dismiss
    -0.25
     KIND
    -0.25
    è®°å¿ĨåĬĽ
    -0.25
     lingu
    -0.25
     presentViewController
    -0.25
    POSITIVE LOGITS
     oportun
    0.29
    ä¸Ģé¡¿
    0.27
    inality
    0.27
    é¡¿
    0.27
     apo
    0.26
    详æĥħ
    0.25
    summ
    0.25
    icated
    0.25
    /people
    0.25
    coords
    0.24
    Activations Density 60.854%

    No Known Activations

    This feature has no known activations.