© 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. 23-TRANSCODER-HP
    7. 23963
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _land
    -0.25
    iffs
    -0.25
    é«ĺæĺĤ
    -0.24
     rural
    -0.24
    ï¼ģ↵↵↵↵
    -0.24
    éĶĭ
    -0.24
    好åIJĹ
    -0.23
    rophic
    -0.23
    MEA
    -0.23
    .flink
    -0.23
    POSITIVE LOGITS
    æĸĩ件
    0.29
    éĩĮçļĦ
    0.28
    ced
    0.28
     вÑģÑĤÑĢ
    0.27
    åı¦ä¸Ģ个
    0.26
    æľī个
    0.26
    äºĴ
    0.26
    éĩĮéĿ¢æľī
    0.25
    åıªæľī
    0.24
    uest
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.