© 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. 27-TRANSCODER-HP
    7. 56333
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     stabilize
    -0.29
     гаÑĢан
    -0.29
    ilib
    -0.27
    ä¼¼
    -0.26
    orta
    -0.24
     stabil
    -0.24
    ÙħÙĨت
    -0.24
    ents
    -0.24
    廪
    -0.23
    ä¼ļåľ¨
    -0.23
    POSITIVE LOGITS
    æľįåĬ¡è´¨éĩı
    0.27
     afterwards
    0.26
    ?><
    0.25
     XCTestCase
    0.24
    posium
    0.24
    ADVERTISEMENT
    0.23
    ä¸ĢåĪ»
    0.23
    ady
    0.23
    人å±ħ
    0.23
    æ¯Ĥ
    0.23
    Activations Density 0.001%

    No Known Activations