© 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. 63484
    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
    (px
    -0.27
    paged
    -0.26
     wraps
    -0.24
     mı
    -0.24
    åħ¨æĿij
    -0.24
    iel
    -0.23
    “My
    -0.23
     bÄħdź
    -0.23
    pth
    -0.23
     pari
    -0.23
    POSITIVE LOGITS
     dangerously
    0.29
    ä¼ģä¸ļæıIJä¾Ľ
    0.29
    мÑĭÑĪ
    0.27
    ä¸ªå·¥ä½ľæĹ¥
    0.26
    è§ŀ
    0.26
    çİ°åĩº
    0.26
    们éĥ½
    0.25
    è¯Ŀ说
    0.25
    è´Łè´£ä»»
    0.25
    è¿ĻäºĽéĥ½æĺ¯
    0.25
    Activations Density 9.017%

    No Known Activations

    This feature has no known activations.