© 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. 109441
    Prev
    Next
    INDEX
    Explanations

    contractions ending in 'd

    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
    çĵ¦
    -0.30
    eki
    -0.26
    缮çļĦæĺ¯
    -0.26
    ä¸ĩä¸Ģ
    -0.25
    çļĦè·¯ä¸Ĭ
    -0.25
    æĽ°
    -0.25
    æĪ¿
    -0.24
    æīĢè¿°
    -0.24
    orable
    -0.24
    æľª
    -0.24
    POSITIVE LOGITS
     yesterday
    0.35
     earlier
    0.32
    è½»è½»åľ°
    0.28
    agra
    0.27
    Yesterday
    0.27
     давно
    0.26
     robbed
    0.26
    stakes
    0.26
     Earlier
    0.26
     previously
    0.26
    Activations Density 0.924%

    No Known Activations