© 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. 18-TRANSCODER-HP
    7. 88918
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heits
    -0.29
    åĽĽæĸ¹
    -0.26
    äºļ马
    -0.26
    æĽ¿æį¢
    -0.26
    arResult
    -0.26
    geh
    -0.26
    grim
    -0.25
    èĬį
    -0.25
    ivery
    -0.24
    ëıħ
    -0.24
    POSITIVE LOGITS
     socially
    0.25
     Zip
    0.25
     Siri
    0.25
    ä¸ĢéĶ®
    0.24
    .sqlite
    0.24
     logically
    0.24
    .bundle
    0.24
    include
    0.24
    void
    0.24
     prevalent
    0.23
    Activations Density 15.037%

    No Known Activations

    This feature has no known activations.