© 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. 27-TRANSCODER-HP
    7. 56575
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     quality
    -0.27
    .Cast
    -0.26
    .imag
    -0.25
    uft
    -0.25
     ripple
    -0.24
    éĢĨ
    -0.24
    åŁ
    -0.24
    æĿĤ
    -0.24
     Offices
    -0.24
    quality
    -0.23
    POSITIVE LOGITS
    iez
    0.27
    tas
    0.27
    ennessee
    0.26
    unnable
    0.25
    اÙĨÙĬØ©
    0.25
    DataContext
    0.24
     Lage
    0.24
    åŃĢ
    0.24
    åĮĸåѦåĵģ
    0.24
    ange
    0.24
    Activations Density 0.025%

    No Known Activations