© 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. 130970
    Prev
    Next
    INDEX
    Explanations

    present

    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
    @s
    -0.29
    åIJIJ
    -0.28
    åĩºèº«
    -0.28
    arked
    -0.27
    åĩºè¡Ģ
    -0.27
    arks
    -0.26
    æĺı
    -0.26
    ImagePath
    -0.26
    害ç¾ŀ
    -0.25
     tucked
    -0.24
    POSITIVE LOGITS
    主æµģ
    0.30
     gal
    0.28
    Ø®Ùħ
    0.26
     modern
    0.26
     global
    0.26
    æľĢåħĪè¿ĽçļĦ
    0.25
     commercial
    0.25
    æŃ¢ãĤģ
    0.25
    åħ¨çIJĥ
    0.25
     contemporary
    0.24
    Activations Density 0.018%

    No Known Activations