© 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. 89490
    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
     drawn
    -0.30
    æ¯Ķä¾ĭ
    -0.30
     DR
    -0.26
    æĬ½
    -0.26
     kho
    -0.25
     eth
    -0.25
     written
    -0.25
     proportion
    -0.25
    æĪIJç«ĭ
    -0.25
     dominant
    -0.24
    POSITIVE LOGITS
    让ä»ĸ们
    0.27
     louis
    0.26
    让æ¶Īè´¹èĢħ
    0.25
    anium
    0.25
    è®©æĽ´å¤ļ
    0.25
    iselect
    0.25
    社ä¼ļä¿ĿéĻ©
    0.24
    lobe
    0.24
    满åĪĨ
    0.24
    èĩ¼
    0.24
    Activations Density 2.263%

    No Known Activations

    This feature has no known activations.