© 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. 25-TRANSCODER-HP
    7. 107193
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pains
    -0.32
    çĸ²åĬ³
    -0.28
    éĹ¾
    -0.28
    .uni
    -0.27
    åı¯ä»¥èİ·å¾Ĺ
    -0.26
    çļĦå¿ĥ
    -0.26
    æľ¬è´¨
    -0.25
    ê²ł
    -0.25
     unborn
    -0.24
    çļĦ责任
    -0.24
    POSITIVE LOGITS
    Ñĥк
    0.27
     compass
    0.27
    .fix
    0.26
    åľ°éľĩ
    0.26
    loud
    0.26
     Earth
    0.26
    osphere
    0.26
     Course
    0.26
    interop
    0.25
    赶
    0.25
    Activations Density 0.912%

    No Known Activations