© 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. 12-TRANSCODER-HP
    7. 22364
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reg
    -0.29
    à¹Ĥà¸Ļ
    -0.27
    ãĥ©ãĥ¼
    -0.27
     OpCode
    -0.26
    èįŃ
    -0.26
    .foundation
    -0.26
    reg
    -0.26
    èļģ
    -0.25
     Ste
    -0.24
    atra
    -0.24
    POSITIVE LOGITS
    :border
    0.25
    accur
    0.25
    keiten
    0.24
    ynchronous
    0.24
    æªIJ
    0.24
     transitional
    0.23
     Clips
    0.23
    åij¨æľŁ
    0.23
    è¿Ļå¥Ĺ
    0.23
    acco
    0.23
    Activations Density 0.000%

    No Known Activations