© 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. 88830
    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
    åºŃ
    -0.28
     InitializeComponent
    -0.27
    å¢ŀéĩı
    -0.26
     gj
    -0.26
    -ie
    -0.26
    DER
    -0.24
    castle
    -0.24
    corn
    -0.24
     forgiven
    -0.24
    zar
    -0.24
    POSITIVE LOGITS
    lev
    0.28
     Wa
    0.27
    aca
    0.27
    èħ±
    0.25
     wa
    0.25
    éĴ³
    0.25
    è¿Ļ个èģĮä¸ļ
    0.25
     role
    0.25
    è¡ĵ
    0.24
    ØŃرÙģ
    0.24
    Activations Density 0.248%

    No Known Activations

    This feature has no known activations.