© 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. 141431
    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
    Pattern
    -0.28
    åı£æ°Ķ
    -0.26
    customize
    -0.26
    .pattern
    -0.26
    åİĮ
    -0.25
    "č↵č↵
    -0.24
    pattern
    -0.24
    Jvm
    -0.23
     Pill
    -0.23
    ngthen
    -0.23
    POSITIVE LOGITS
    unkt
    0.26
     pont
    0.25
    amento
    0.25
    INGTON
    0.24
    鼶éĥ¨ä»¶
    0.24
    èį
    0.24
    ENTITY
    0.23
    ØŃÙĪ
    0.23
    asta
    0.23
    ccione
    0.23
    Activations Density 12.964%

    No Known Activations

    This feature has no known activations.