© 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. 98072
    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
    çīĴ
    -0.26
    ÑĢоÑģ
    -0.25
     userList
    -0.25
     kut
    -0.24
    ivent
    -0.24
    ä¸Ģ度
    -0.24
    /ros
    -0.23
     roam
    -0.23
     consenting
    -0.23
    EVER
    -0.23
    POSITIVE LOGITS
    åij¨æľŁ
    0.26
    ä¸ĢåĪĢ
    0.25
    ç¢Ĺ
    0.25
    ande
    0.25
    pro
    0.24
    ·¨
    0.24
     HtmlWebpackPlugin
    0.23
     currently
    0.23
    å¹´åĨħ
    0.23
    landscape
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.