© 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. 88963
    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
    ialis
    -0.29
    ä½łéľĢè¦ģ
    -0.27
     Romero
    -0.26
    èį·
    -0.26
    mods
    -0.24
     leo
    -0.24
    udo
    -0.23
    ä¹ĭ称
    -0.23
    Founder
    -0.23
    XI
    -0.23
    POSITIVE LOGITS
     Translation
    0.29
    èĭ±æĸĩ
    0.28
    ((__
    0.28
    EncodingException
    0.27
    translation
    0.26
    ä¸Ńæĸĩ
    0.26
    __,↵
    0.26
    assic
    0.25
    Translation
    0.25
    гÑĢан
    0.24
    Activations Density 4.818%

    No Known Activations

    This feature has no known activations.