© 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. 88419
    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
     Mile
    -0.27
    +-+-+-+-
    -0.27
    zos
    -0.26
    patible
    -0.25
     discrete
    -0.24
    ,âĢ¦↵↵
    -0.24
    è¿Ļä¹Īä¹ħ
    -0.24
    &↵
    -0.24
    dependent
    -0.23
    /+
    -0.23
    POSITIVE LOGITS
    约æĿŁ
    0.27
    ÙĤÙĨ
    0.26
     stuck
    0.26
    maj
    0.25
    管å±Ģ
    0.25
    _tra
    0.25
    cover
    0.24
    å¾Ģå¤ĸ
    0.24
    åĦ¿
    0.24
    ngo
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.