© 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. 22-TRANSCODER-HP
    7. 87924
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Same
    -0.27
    uplicate
    -0.27
    arus
    -0.26
    itat
    -0.26
    .si
    -0.25
    éĺħ读åħ¨æĸĩ
    -0.25
    onus
    -0.25
    åŃ
    -0.24
    èĮħ
    -0.24
    åħ¸åŀĭ
    -0.24
    POSITIVE LOGITS
     adaptive
    0.31
     Adaptive
    0.28
     adapt
    0.28
     strokes
    0.27
    -strokes
    0.27
     stroke
    0.26
    stroke
    0.26
    该éĻ¢
    0.26
    LayoutManager
    0.26
     adap
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.