© 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. 130004
    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
    æľ¬è´¨ä¸Ĭ
    -0.26
    並ä¸Ķ
    -0.26
    arr
    -0.26
    Attached
    -0.26
    Sort
    -0.25
    å»ĵ
    -0.24
    æĬ±çĿĢ
    -0.23
     pics
    -0.23
    een
    -0.23
     inter
    -0.23
    POSITIVE LOGITS
    buch
    0.27
     rhe
    0.25
     requestOptions
    0.24
    åĭĩ
    0.24
    å¸ĥå°Ķ
    0.24
    ä¾
    0.23
    lyph
    0.23
    ;element
    0.23
    stice
    0.23
    anzi
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.