© 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. 89475
    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
    æıIJ
    -0.26
    é£ı
    -0.26
    建åįİ
    -0.25
    kening
    -0.24
    èĬĬ
    -0.24
    åºŁçī©
    -0.24
    peech
    -0.24
    -has
    -0.23
    éĺħ读
    -0.23
    ело
    -0.23
    POSITIVE LOGITS
    guild
    0.25
    arem
    0.24
    burgh
    0.24
    æ°´åºĵ
    0.24
     washing
    0.24
     Guides
    0.23
    æŃ»åİ»
    0.23
    isks
    0.23
    ials
    0.23
     blat
    0.23
    Activations Density 2.398%

    No Known Activations

    This feature has no known activations.