© 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. 9-TRANSCODER-HP
    7. 30267
    Prev
    Next
    INDEX
    Explanations

    legal system forgiveness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĬĺ
    -0.29
     fold
    -0.28
    zd
    -0.26
    oha
    -0.26
    ctp
    -0.26
    AWN
    -0.26
     sched
    -0.25
    itur
    -0.25
     Fold
    -0.25
    _fold
    -0.25
    POSITIVE LOGITS
    unch
    0.30
     bon
    0.28
    è´«è¡Ģ
    0.27
    æŃĩ
    0.27
    åħ¥éŨ
    0.27
     EXPORT
    0.26
    Quit
    0.25
    ä¼ĺ
    0.25
    æł¹åŁº
    0.25
    Ing
    0.24
    Activations Density 0.099%

    No Known Activations