© 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. 32-TRANSCODER-HP
    7. 40975
    Prev
    Next
    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    檫
    -0.29
    igin
    -0.26
     realizes
    -0.26
    -pl
    -0.25
    å¾Ģä¸Ĭ
    -0.25
    inidad
    -0.25
    æķijåij½
    -0.25
    æĺŁåħī
    -0.24
    çŀ¬éĹ´
    -0.24
    æħ¥
    -0.24
    POSITIVE LOGITS
    æĿ¥èĩª
    0.29
    иÑĢовка
    0.28
     drv
    0.27
    ilha
    0.26
    çļĦè¯Ŀ
    0.26
    åĢº
    0.25
    иÑĢовки
    0.25
    ativo
    0.25
    ศาล
    0.25
    æĤ¨çļĦ
    0.24
    Activations Density 0.001%

    No Known Activations