© 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. 30-TRANSCODER-HP
    7. 96918
    Prev
    Next
    INDEX
    Explanations

    web code and blog text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     borderColor
    -0.27
    塵
    -0.26
    客æłĪ
    -0.25
    LEGRO
    -0.25
    辩æĬ¤
    -0.24
    atu
    -0.24
    .getMethod
    -0.24
    çļĦæ°Ķæģ¯
    -0.24
     judgment
    -0.24
    æĸĵ
    -0.24
    POSITIVE LOGITS
    ring
    0.27
     commit
    0.27
    oss
    0.27
    rien
    0.27
    ruk
    0.26
    æľĿ
    0.26
    Domain
    0.26
    ç©¿
    0.26
    hev
    0.26
    zi
    0.25
    Activations Density 0.008%

    No Known Activations