© 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. 89265
    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
    ulet
    -0.30
    å±İ
    -0.27
    udu
    -0.26
    missive
    -0.26
    âĩĵ
    -0.26
    <<(
    -0.25
    gage
    -0.25
    帮ä»ĸ
    -0.25
    worm
    -0.24
    æıIJæĹ©
    -0.24
    POSITIVE LOGITS
    IFS
    0.28
    rons
    0.28
    bserv
    0.27
    æĸ¯é¡¿
    0.27
     oss
    0.26
    è£Ł
    0.26
     nin
    0.26
     ic
    0.26
    ender
    0.25
     ether
    0.25
    Activations Density 1.323%

    No Known Activations

    This feature has no known activations.