© 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. 113082
    Prev
    Next
    INDEX
    Explanations

    Money and business

    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
     porr
    -0.28
     sling
    -0.27
    æľīæķĪæĢ§
    -0.26
     paranormal
    -0.25
     Deadly
    -0.25
    .blog
    -0.24
    _MEDIUM
    -0.24
     peeled
    -0.24
     moy
    -0.23
    erness
    -0.23
    POSITIVE LOGITS
     money
    0.42
    money
    0.36
    çIJĨè´¢
    0.36
    交æĺĵ
    0.35
    éĩijé¢Ŀ
    0.35
    è´§å¸ģ
    0.34
     Money
    0.34
    Money
    0.33
     transaction
    0.32
     wallet
    0.32
    Activations Density 0.029%

    No Known Activations