© 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. 89008
    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
    æŃ£å¸¸çļĦ
    -0.31
    主导
    -0.29
    ä½İä½į
    -0.27
     costs
    -0.27
     unde
    -0.27
    ypass
    -0.26
     successful
    -0.26
    çŁ¥æĻĵ
    -0.25
     dominates
    -0.25
     favourable
    -0.25
    POSITIVE LOGITS
    bservice
    0.33
     bre
    0.27
    çł´
    0.27
    alez
    0.26
     ApiController
    0.25
    éĩįçİ°
    0.25
     gcd
    0.25
    áĥĸ
    0.24
    马ä¸ģ
    0.24
    mates
    0.24
    Activations Density 3.991%

    No Known Activations

    This feature has no known activations.