© 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. 27-TRANSCODER-HP
    7. 8691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åģľ
    -0.28
    p
    -0.28
    è°ļ
    -0.28
    åij½
    -0.26
    agnostics
    -0.26
     Noon
    -0.26
    Life
    -0.25
    enders
    -0.25
    ending
    -0.24
    life
    -0.24
    POSITIVE LOGITS
    arness
    0.34
     mee
    0.27
    æĮ½
    0.26
    å¥Ĺ
    0.26
    ceu
    0.25
    mát
    0.25
     dint
    0.24
    NSDictionary
    0.24
    å¿ĹæĦ¿
    0.23
    .tencent
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.