© 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. 33-TRANSCODER-HP
    7. 53773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purchase
    -0.82
    è´Ńä¹°
    -0.82
     purchasing
    -0.82
     buying
    -0.81
     buy
    -0.80
    ä¹°
    -0.79
    è´Ń
    -0.78
    ä¹°äºĨ
    -0.73
     Buy
    -0.73
     Purchase
    -0.72
    POSITIVE LOGITS
    Spl
    0.32
     spl
    0.32
     sh
    0.31
    sh
    0.30
     Spl
    0.30
     Shen
    0.29
    spl
    0.29
    -sh
    0.28
    æļĦ
    0.27
    ÑĪи
    0.27
    Activations Density 0.222%

    No Known Activations