© 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. 108599
    Prev
    Next
    INDEX
    Explanations

    Technical problems/troubleshooting

    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
    ·æĸ°
    -0.29
    æĭĹ
    -0.29
    .AsyncTask
    -0.27
    Synopsis
    -0.26
    MeasureSpec
    -0.26
    ä¸ĩäºĭ
    -0.25
    essian
    -0.25
    æģĴ大
    -0.24
    employment
    -0.24
    å¾ĹåĪĨ
    -0.24
    POSITIVE LOGITS
    жа
    0.31
    жÑĥ
    0.26
    çīĮåŃIJ
    0.25
    ç«ĭãģ¡
    0.25
    nob
    0.25
    lication
    0.24
    née
    0.24
    named
    0.24
    nel
    0.24
     herself
    0.23
    Activations Density 5.281%

    No Known Activations