© 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. 19-TRANSCODER-HP
    7. 8839
    Prev
    Next
    INDEX
    Explanations

    code, age, and English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymax
    -0.28
    éĤ£æ¬¡
    -0.28
    ä¹°åįķ
    -0.26
    urban
    -0.25
    太å°ij
    -0.25
    æĪijçľĭ
    -0.25
    æĺ¯ä»Ģä¹Īåij¢
    -0.25
    éĤ£æŶåĢĻ
    -0.25
    çļĦèĦļæŃ¥
    -0.24
     versa
    -0.24
    POSITIVE LOGITS
    年级
    0.26
    entions
    0.25
    Disposed
    0.25
    kräfte
    0.25
     Hosp
    0.24
    .nih
    0.24
    ники
    0.24
    elles
    0.24
     Suffolk
    0.23
     Thoughts
    0.23
    Activations Density 0.005%

    No Known Activations