© 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. 89095
    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
    å±ķå¼Ģ
    -0.33
    mes
    -0.31
     rec
    -0.28
     unst
    -0.26
    æ·±åĮĸ
    -0.26
     dem
    -0.26
    lingen
    -0.26
    妹åŃIJ
    -0.25
    ahr
    -0.25
    nÄħ
    -0.25
    POSITIVE LOGITS
    ESCO
    0.26
    :start
    0.25
    ervised
    0.25
    .ArgumentParser
    0.25
    第ä¹Ŀ
    0.25
     Phaser
    0.25
     Cookbook
    0.25
    第åħ«
    0.25
    第äºĶ
    0.24
     Actors
    0.24
    Activations Density 9.244%

    No Known Activations

    This feature has no known activations.