© 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. 12-TRANSCODER-HP
    7. 22104
    Prev
    Next
    INDEX
    Explanations

    Names (Powell, Doug)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Tun
    -0.28
    tracts
    -0.28
    unnable
    -0.25
    Sharper
    -0.25
    å¤ĩ
    -0.25
     troch
    -0.24
     serialVersionUID
    -0.24
     tuning
    -0.23
     Strait
    -0.23
    åĪ»
    -0.23
    POSITIVE LOGITS
    MEA
    0.26
    æĺ¯éŁ©åĽ½
    0.25
     ÐľÐ¾
    0.24
     lief
    0.24
    >(()
    0.24
    ÑĩаÑĤ
    0.24
    reon
    0.24
    ë°
    0.24
    ÑīиÑĤ
    0.24
    akit
    0.23
    Activations Density 0.002%

    No Known Activations