© 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. 88624
    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
    oux
    -0.28
    åį¯
    -0.27
    è¨ĩ
    -0.27
    æ¥Ŀ
    -0.26
    eron
    -0.26
    ./
    -0.26
    æĸ°åĬ¨èĥ½
    -0.26
    ·æĸ°
    -0.25
    nings
    -0.24
    åIJĦ个æĸ¹éĿ¢
    -0.24
    POSITIVE LOGITS
     porr
    0.28
    vet
    0.27
    quat
    0.26
     harassed
    0.26
    iate
    0.26
     differentiate
    0.25
    éĢĥéģ¿
    0.25
    organic
    0.24
    unds
    0.24
     penn
    0.24
    Activations Density 29.245%

    No Known Activations

    This feature has no known activations.