© 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. 22-TRANSCODER-HP
    7. 88943
    Prev
    Next
    INDEX
    Explanations

    Personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    é¥Ń
    -0.32
    éļĶ
    -0.27
    cient
    -0.26
    /copyleft
    -0.26
    inous
    -0.26
    cents
    -0.26
    大éĿ¢ç§¯
    -0.26
    æĦŁ
    -0.25
    łģ
    -0.25
    İĺìĿ´
    -0.25
    POSITIVE LOGITS
     Wikipedia
    0.25
    ido
    0.25
    usat
    0.24
    [](
    0.23
    æĺ¯æĪijçļĦ
    0.23
     my
    0.23
    icate
    0.23
    楼ä¸ĭ
    0.22
    igo
    0.22
    leston
    0.22
    Activations Density 0.028%

    No Known Activations