© 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. 19-TRANSCODER-HP
    7. 9624
    Prev
    Next
    INDEX
    Explanations

    Relative pronouns/linking verbs

    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
    Negative Logits
     Trident
    -0.27
     guaranteed
    -0.27
    eki
    -0.26
    ä¸ĩåħ¬éĩĮ
    -0.26
     guarantees
    -0.26
    elor
    -0.26
     guarantee
    -0.24
     til
    -0.24
    æ¼Ĥ
    -0.24
     Climate
    -0.24
    POSITIVE LOGITS
    ç¬Ķ
    0.29
    çıĢ
    0.28
    utron
    0.26
     figur
    0.26
    ¦Ĥ
    0.26
    æĢ§è´¨
    0.24
    odb
    0.24
    èµ£å·ŀ
    0.24
     stakes
    0.24
    amber
    0.24
    Activations Density 0.041%

    No Known Activations