© 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. 20-TRANSCODER-HP
    7. 108781
    Prev
    Next
    INDEX
    Explanations

    differences/lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     loạt
    -0.29
    eno
    -0.26
    å±Ĥ次
    -0.25
    xDF
    -0.25
    atories
    -0.24
    ÑĢÑĥÑĤ
    -0.24
    åĩ¡æľ¬ç½ij
    -0.24
    çµĦ
    -0.24
    enth
    -0.23
    ierarchical
    -0.23
    POSITIVE LOGITS
    åĿıäºĨ
    0.27
    ä¹ł
    0.27
    COMMON
    0.26
     ja
    0.26
    éĹ¹
    0.26
     {}).
    0.25
     either
    0.25
    éĻį
    0.24
    çĨŁæĤī
    0.24
    çļĦ主è¦ģ
    0.24
    Activations Density 56.747%

    No Known Activations