© 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. 20-TRANSCODER-HP
    7. 62665
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĤİ
    -0.29
    rangle
    -0.28
    çģµ
    -0.26
    åĬŀåħ¬æ¥¼
    -0.26
     Caldwell
    -0.25
     barg
    -0.25
     missed
    -0.24
    ialis
    -0.24
    宫殿
    -0.23
     palace
    -0.23
    POSITIVE LOGITS
     Voll
    0.27
    éĶµ
    0.27
    =UTF
    0.25
    身
    0.25
    body
    0.25
     thinner
    0.25
    身ä¸Ĭ
    0.24
    TAG
    0.24
     recipients
    0.24
    éķľ
    0.24
    Activations Density 9.538%

    No Known Activations