© 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. 129067
    Prev
    Next
    INDEX
    Explanations

    Code assignments and lists

    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
    ProcessEvent
    -0.31
    -0.27
    éĽ¾
    -0.24
    æŃ£ç¡®çļĦ
    -0.24
    åį³å°Ĩ
    -0.24
    äºĮåįģå¹´
    -0.24
     car
    -0.24
     media
    -0.24
     reg
    -0.24
    **
    -0.23
    POSITIVE LOGITS
    dojo
    0.27
    ÃŃda
    0.26
    -Nov
    0.26
    ually
    0.25
    -Cs
    0.24
    -New
    0.24
     Zahl
    0.24
    achsen
    0.24
    ison
    0.24
    edly
    0.24
    Activations Density 0.059%

    No Known Activations