© 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. 43068
    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
    ï½ŀ↵↵
    -0.27
    天空
    -0.27
    bove
    -0.26
    +xml
    -0.26
    ald
    -0.26
     horizon
    -0.25
    eyed
    -0.25
    aise
    -0.24
    ohon
    -0.24
    aket
    -0.24
    POSITIVE LOGITS
     outs
    0.33
    -out
    0.27
    ught
    0.27
     Out
    0.26
    åĩºæĿ¥
    0.26
    etta
    0.26
     pad
    0.25
    pad
    0.25
     OUT
    0.25
     Dot
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.