© 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. 89322
    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
    便
    -0.29
    ocide
    -0.28
    æİ¡
    -0.25
    å¥ĸåѦéĩij
    -0.24
    oku
    -0.24
     hostage
    -0.24
     frustr
    -0.24
    ç»ıèIJ¥èĮĥåĽ´
    -0.24
    粪
    -0.24
    æĺ¼å¤ľ
    -0.24
    POSITIVE LOGITS
    ERO
    0.30
    ispers
    0.25
    æį·
    0.25
    (concat
    0.25
    ngrx
    0.25
     however
    0.24
    ICS
    0.24
    exchange
    0.24
    arrays
    0.24
     Paths
    0.24
    Activations Density 26.439%

    No Known Activations

    This feature has no known activations.