© 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. 130598
    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
    认
    -0.27
    ators
    -0.27
    ator
    -0.26
    eral
    -0.24
     too
    -0.23
     exchanged
    -0.23
     exchange
    -0.23
     collectively
    -0.23
    ades
    -0.23
    arian
    -0.23
    POSITIVE LOGITS
     Commod
    0.24
    æī£
    0.24
    ranges
    0.24
    毡
    0.24
    çī¹èī²çļĦ
    0.23
     Initialise
    0.23
     Dip
    0.23
    åĵķ
    0.23
     Views
    0.23
    æħij
    0.22
    Activations Density 0.179%

    No Known Activations

    This feature has no known activations.