© 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. 30-TRANSCODER-HP
    7. 97000
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¦ĨçĽĸçİĩ
    -0.28
    rastructure
    -0.27
     Cay
    -0.26
    utilities
    -0.25
    #!
    -0.25
     Souls
    -0.25
    åIJīåĪ©
    -0.24
     parsley
    -0.24
    addons
    -0.24
    spinner
    -0.24
    POSITIVE LOGITS
     character
    0.34
     childhood
    0.33
    zug
    0.32
     characters
    0.31
     characterization
    0.30
     account
    0.29
    arent
    0.28
     conflict
    0.28
     Character
    0.27
    alink
    0.27
    Activations Density 0.895%

    No Known Activations