© 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. 42322
    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
    Speaking
    -0.27
    款
    -0.27
    quis
    -0.26
     next
    -0.25
    主è¦ģæĺ¯
    -0.25
    tic
    -0.24
     Cli
    -0.24
    development
    -0.24
     Gram
    -0.24
    èĩĤ
    -0.24
    POSITIVE LOGITS
    æľ¬æĬ¥
    0.28
    赶ä¸Ĭ
    0.28
    ä¸Ńéĵģ
    0.28
    _DS
    0.27
    yar
    0.27
    esty
    0.25
    çĺĹ
    0.24
     Hasan
    0.24
    .btnSave
    0.24
    åİĤåĮº
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.