© 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. 32-TRANSCODER-HP
    7. 43262
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĪæł¼
    -0.27
    æľīä½ķ
    -0.26
     criter
    -0.26
    uhan
    -0.25
    ä¸įåIJĪæł¼
    -0.25
    coding
    -0.25
     launder
    -0.25
    åĩºå±Ģ
    -0.25
    waters
    -0.25
     succinct
    -0.24
    POSITIVE LOGITS
    Trip
    0.26
     Trip
    0.25
    companies
    0.25
    侧
    0.25
    ä¸Ńå¤ĸ
    0.24
    两家
    0.24
    管çIJĨæ°´å¹³
    0.24
    translation
    0.24
    partment
    0.23
    entered
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.