© 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. 130323
    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
    <LM
    -0.30
    æŁ³
    -0.29
    -net
    -0.27
    jem
    -0.26
    ETY
    -0.25
    æ»ķ
    -0.25
    .dw
    -0.25
    addChild
    -0.25
    å¥Ī
    -0.24
    voy
    -0.24
    POSITIVE LOGITS
     scr
    0.29
     expl
    0.28
    Cor
    0.28
    ä¸Ģåı£
    0.28
    èŁ
    0.27
     atr
    0.26
    streams
    0.26
    COR
    0.26
    .upper
    0.26
     qual
    0.25
    Activations Density 38.793%

    No Known Activations

    This feature has no known activations.