© 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. 63524
    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
    thead
    -0.26
     atom
    -0.25
    ç²ľ
    -0.25
    _accessible
    -0.24
    åħī彩
    -0.24
    atom
    -0.24
    对æĪijæĿ¥è¯´
    -0.23
    ÇĶ
    -0.23
     اÙĦØŃÙĬ
    -0.23
     uns
    -0.23
    POSITIVE LOGITS
    vo
    0.27
     Moving
    0.26
     moving
    0.26
     Glas
    0.25
     anmeld
    0.25
    ldata
    0.25
    uyen
    0.25
    .nz
    0.25
    ogan
    0.24
    opause
    0.24
    Activations Density 28.638%

    No Known Activations

    This feature has no known activations.