© 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. 111705
    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
     readings
    -0.27
    ä¹ĥ
    -0.27
     ok
    -0.24
    å¼¹
    -0.24
    æĸ¹
    -0.24
     reading
    -0.23
     Bull
    -0.23
    Tpl
    -0.23
    spl
    -0.23
    读
    -0.23
    POSITIVE LOGITS
    éĹ®ä»ĸ
    0.26
    åºĶåľ¨
    0.24
    æĭĽåij¼
    0.23
     sơ
    0.23
    åĴ½
    0.23
    yne
    0.23
    åĸĿäºĨ
    0.23
     Gregg
    0.23
    ä¼ļåIJĮ
    0.23
    trade
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.