© 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. 89672
    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
    èĸ®
    -0.27
    arer
    -0.27
    -abs
    -0.24
     cuckold
    -0.24
    oreal
    -0.24
    å©ļ
    -0.23
    rio
    -0.23
    缸çĪ±
    -0.23
     underwent
    -0.23
    hei
    -0.23
    POSITIVE LOGITS
     affirmation
    0.26
    iders
    0.26
     bag
    0.24
    컬
    0.24
    emies
    0.24
    lng
    0.23
     witnesses
    0.23
    éģĵå¾·
    0.23
    -resources
    0.23
    getResource
    0.23
    Activations Density 22.458%

    No Known Activations

    This feature has no known activations.