© 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. 63801
    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
    èĦī
    -0.31
     mandate
    -0.28
    .il
    -0.27
    佩
    -0.25
    unist
    -0.24
    çļĦåıijçĶŁ
    -0.24
    atisation
    -0.24
    .minecraft
    -0.24
     minecraft
    -0.24
    inerary
    -0.23
    POSITIVE LOGITS
    úng
    0.25
    çĭİ
    0.24
    entai
    0.24
    oras
    0.24
    à°²
    0.24
     vac
    0.24
    uspended
    0.24
    ä½łè¿ĺ
    0.24
    èĻİ
    0.24
    änger
    0.24
    Activations Density 12.584%

    No Known Activations

    This feature has no known activations.