© 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. 87484
    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
    åĵ¨
    -0.31
    ports
    -0.25
    缮åīį
    -0.24
    å·©
    -0.24
    åĪĨè¡Į
    -0.23
    被åĬ¨
    -0.23
     others
    -0.23
    _stylesheet
    -0.22
    åIJĮåѦ
    -0.22
     Cory
    -0.22
    POSITIVE LOGITS
     multis
    0.24
     remot
    0.24
    åģļ人
    0.23
    draft
    0.23
     suspicion
    0.23
    _draft
    0.23
    hunt
    0.23
    æĢĢçĸij
    0.23
     DISPATCH
    0.22
    ksz
    0.22
    Activations Density 0.813%

    No Known Activations

    This feature has no known activations.