© 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. 63303
    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
    posed
    -0.27
    wstring
    -0.26
    ackbar
    -0.26
     timely
    -0.24
    .setContentType
    -0.24
    neau
    -0.24
     masses
    -0.24
    .setString
    -0.24
    stra
    -0.24
    大å°ı
    -0.24
    POSITIVE LOGITS
     Prem
    0.28
    代
    0.28
     reserve
    0.27
    è¿ĺæĺ¯ä¼ļ
    0.27
    mith
    0.26
    éĻįèIJ½
    0.26
    åľ¨çİ°åľº
    0.26
    æľīåħ´è¶£
    0.25
    imately
    0.25
    è¿ĺæĺ¯
    0.24
    Activations Density 0.317%

    No Known Activations

    This feature has no known activations.