© 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. 14-TRANSCODER-HP
    7. 39670
    Prev
    Next
    INDEX
    Explanations

    Code, licenses, or locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    visor
    -0.30
     courts
    -0.28
     Courts
    -0.26
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.26
    uges
    -0.26
    erves
    -0.26
    æ§
    -0.26
    åıij表äºĨ
    -0.25
    综åIJĪ
    -0.25
    itories
    -0.25
    POSITIVE LOGITS
    aton
    0.28
    çļĦçĶŁåij½
    0.25
     invasion
    0.25
    GroupName
    0.24
    å¤ľæĻļ
    0.24
    .LAZY
    0.24
    ovah
    0.23
    .CommandType
    0.23
    _BROWSER
    0.23
    enumer
    0.23
    Activations Density 0.174%

    No Known Activations