© 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. 89014
    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
     hyper
    -0.25
    eb
    -0.24
    ä¸ĵä¸ļ人士
    -0.24
    æĽ´ä½İ
    -0.23
    echa
    -0.23
    太ä¹ħ
    -0.23
     Hammond
    -0.23
    utral
    -0.23
    amu
    -0.22
    Incre
    -0.22
    POSITIVE LOGITS
    åĽ¾ä¸º
    0.24
    ä¼Ļ
    0.23
    unch
    0.23
    å©¿
    0.23
    åĮĸçļĦ
    0.22
    èµ°
    0.22
    .sep
    0.22
    æ°ijæĹıæĸĩåĮĸ
    0.22
    rr
    0.22
    /wp
    0.22
    Activations Density 1.096%

    No Known Activations

    This feature has no known activations.