© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111067
    Prev
    Next
    INDEX
    Explanations

    code 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
    Negative Logits
    å¹´éĻIJ
    -0.34
     age
    -0.32
    å±Ĥ次
    -0.31
     heights
    -0.29
    åĽ½ç±į
    -0.29
    de
    -0.28
    ä»·ä½į
    -0.28
     timeframe
    -0.28
     ages
    -0.27
    ç¨ĭ度
    -0.27
    POSITIVE LOGITS
    ).__
    0.32
    essional
    0.27
    ect
    0.25
    ]int
    0.24
    _again
    0.24
     Hold
    0.24
    isory
    0.23
    iliate
    0.23
     Bauer
    0.23
     Kern
    0.23
    Activations Density 0.004%

    No Known Activations