© 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. 131219
    Prev
    Next
    INDEX
    Explanations

    accessibility accommodations

    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
     mug
    -0.25
    æĻ¯
    -0.24
    lamp
    -0.24
    еÑĢÑĤ
    -0.24
    ç½¢
    -0.23
    acen
    -0.23
    æŦ
    -0.23
    esan
    -0.23
    imer
    -0.23
     ball
    -0.23
    POSITIVE LOGITS
    è¿ĩçļĦ
    0.28
     reluctant
    0.28
    çĸı导
    0.27
    ster
    0.25
     encour
    0.25
    太éĺ³åŁİ
    0.25
    isto
    0.24
    aten
    0.24
    æĶ¯
    0.24
    STER
    0.24
    Activations Density 0.005%

    No Known Activations