© 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. 140662
    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
    éĩİ
    -0.28
     forward
    -0.28
    veis
    -0.25
    ék
    -0.25
    ãĤĤãģ®ãģ®
    -0.25
    ;break
    -0.25
    forward
    -0.24
    wise
    -0.24
    odom
    -0.24
    åīįåĪĹ
    -0.24
    POSITIVE LOGITS
    tml
    0.26
     Urdu
    0.25
    å¿ĥéĩĮ
    0.24
    uctions
    0.23
    icia
    0.23
    èĭİ
    0.23
    isable
    0.23
    descriptor
    0.23
    asia
    0.23
     Plasma
    0.22
    Activations Density 15.315%

    No Known Activations