© 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. 89231
    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
     formulas
    -0.28
    lays
    -0.28
     experiments
    -0.25
    åĪ©çĶ¨æĤ¨çļĦ
    -0.24
    ä¸ĢçĤ¹åĦ¿
    -0.24
    èĬĭ
    -0.24
    åģļä¸ĢäºĽ
    -0.23
    ekte
    -0.23
     errors
    -0.23
     experimenting
    -0.23
    POSITIVE LOGITS
     vista
    0.31
    ·»
    0.29
    ulum
    0.28
    erland
    0.28
    ottom
    0.27
     BLL
    0.27
    edly
    0.27
    ypress
    0.25
    keit
    0.25
     propre
    0.24
    Activations Density 2.048%

    No Known Activations

    This feature has no known activations.