© 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. 129042
    Prev
    Next
    INDEX
    Explanations

    opportunities, services, programs

    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
     scared
    -0.27
     ÑģебÑı
    -0.27
     afford
    -0.27
    çļĦç¬ij容
    -0.26
    _vi
    -0.25
    第äºĮ次
    -0.25
     yourselves
    -0.24
    rik
    -0.24
    æĥ§
    -0.24
     computation
    -0.24
    POSITIVE LOGITS
    rud
    0.30
    éĺĶ
    0.29
    许å¤ļ
    0.29
    Connecting
    0.27
    åįij
    0.26
    äºĽ
    0.25
    çŀĦ
    0.25
    aras
    0.25
    anus
    0.24
     addAction
    0.24
    Activations Density 0.013%

    No Known Activations