© 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. 89158
    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
     fian
    -0.28
    wüns
    -0.27
    çĻ¾å¼º
    -0.26
     æĽ
    -0.25
    zia
    -0.25
    æĬµæĬĹåĬĽ
    -0.24
     Redemption
    -0.24
    ktop
    -0.24
    -publish
    -0.23
    ÙħÙĪÙĦ
    -0.23
    POSITIVE LOGITS
     sweeping
    0.30
    æī«
    0.29
    oge
    0.28
    .pg
    0.27
    ubo
    0.26
    Macro
    0.26
    åŁĤ
    0.26
     elim
    0.26
    罩
    0.26
    ç»ĵæĿŁ
    0.25
    Activations Density 2.667%

    No Known Activations

    This feature has no known activations.