© 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. 141664
    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
    belief
    -0.27
    åĴĮå®ĮåĸĦ
    -0.26
     Ahmad
    -0.25
    éĴĬ
    -0.25
    -driver
    -0.25
     noses
    -0.24
    建åħļ
    -0.23
    backward
    -0.23
    completion
    -0.23
    phan
    -0.23
    POSITIVE LOGITS
    orda
    0.28
    kr
    0.26
    ervoir
    0.24
     pip
    0.24
    .wind
    0.24
    htt
    0.24
    ipp
    0.24
     invent
    0.23
     Trit
    0.23
    cope
    0.23
    Activations Density 2.014%

    No Known Activations

    This feature has no known activations.