© 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. 88812
    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
    æĴij
    -0.27
    èĭĩ
    -0.26
    æľªæĿ¥çļĦ
    -0.26
    edList
    -0.26
    ayed
    -0.26
    åĬ©
    -0.25
    oration
    -0.25
    伤åı£
    -0.24
    ÑĢев
    -0.24
    ä¼ģä¸ļæıIJä¾Ľ
    -0.24
    POSITIVE LOGITS
    ertext
    0.26
    itaire
    0.25
    twor
    0.24
     Cruiser
    0.23
     Tart
    0.23
     Garage
    0.22
    ç»Ŀ对
    0.22
    ɵ
    0.22
     satur
    0.22
    æµł
    0.22
    Activations Density 1.884%

    No Known Activations

    This feature has no known activations.