© 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. 129133
    Prev
    Next
    INDEX
    Explanations

    Young people

    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
    cheiden
    -0.27
    æĪIJè´¥
    -0.26
    é£İåħī
    -0.26
    ç¥Ŀ
    -0.25
    ÑĢеб
    -0.24
     hustle
    -0.24
    das
    -0.24
    è¿Ļ个人
    -0.23
    getto
    -0.23
    reff
    -0.23
    POSITIVE LOGITS
     "")↵↵
    0.28
     blanks
    0.28
     explan
    0.27
     ""),
    0.25
    IONS
    0.25
     _)
    0.25
     exper
    0.25
    è®®
    0.25
     "↵↵
    0.25
    .React
    0.24
    Activations Density 0.007%

    No Known Activations