© 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. 107323
    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
    aran
    -0.24
    sl
    -0.24
    åĮĿ
    -0.24
    sheet
    -0.24
    inar
    -0.23
    .currentThread
    -0.23
    书记
    -0.23
    quals
    -0.23
     nil
    -0.23
    enne
    -0.22
    POSITIVE LOGITS
    èĥº
    0.24
    .um
    0.24
    (ec
    0.24
    äºĨä»ĸçļĦ
    0.23
    vae
    0.23
    ://${
    0.23
    łéĻ¤
    0.23
    åı¦ä¸Ģä½į
    0.23
    åıªçŁ¥éģĵ
    0.23
    )o
    0.23
    Activations Density 3.408%

    No Known Activations

    This feature has no known activations.