© 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. 129381
    Prev
    Next
    INDEX
    Explanations

    Code/text snippets

    np_max-act · gemini-2.0-flash
    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
    LIB
    -0.29
    ç¨Ģ
    -0.25
    社ä¼ļåĮĸ
    -0.25
    æĬ½
    -0.24
    æĿ¾
    -0.24
     pump
    -0.24
    .EventQueue
    -0.23
    èIJĭ
    -0.23
    .GetLength
    -0.23
    ulti
    -0.23
    POSITIVE LOGITS
    kest
    0.28
     intent
    0.27
    æĢģ度
    0.27
    jong
    0.26
    表çİ°åĩº
    0.26
     intention
    0.25
    beck
    0.25
    .intent
    0.24
    æĥ³äºĨæĥ³
    0.24
    kie
    0.24
    Activations Density 0.001%

    No Known Activations