© 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. 108248
    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
    positor
    -0.29
     Equivalent
    -0.28
     TIM
    -0.25
    ippers
    -0.25
    Equivalent
    -0.25
     Mercury
    -0.24
    Congratulations
    -0.24
    éĩįæķ´
    -0.24
    ListGroup
    -0.24
     Ore
    -0.23
    POSITIVE LOGITS
    tele
    0.28
    kes
    0.27
    åĩĨåħ¥
    0.26
    orks
    0.26
     springfox
    0.26
     hire
    0.26
     leverage
    0.25
     thái
    0.25
    lide
    0.25
     "@/
    0.24
    Activations Density 4.234%

    No Known Activations

    This feature has no known activations.