© 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. 23-TRANSCODER-HP
    7. 25598
    Prev
    Next
    INDEX
    Explanations

    Core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .AddComponent
    -0.29
    .CreateInstance
    -0.27
    ório
    -0.27
    ismet
    -0.26
    åıĤ
    -0.25
    _spacing
    -0.24
     Taste
    -0.24
    èĩªåıij
    -0.24
     Bounds
    -0.24
     BJ
    -0.23
    POSITIVE LOGITS
    SMART
    0.28
    äºĨäºĽ
    0.27
    metic
    0.27
    äºĭ實
    0.26
     deal
    0.25
    th
    0.25
    æ¥Ķ
    0.25
    y
    0.24
     lookout
    0.24
    atable
    0.23
    Activations Density 2.691%

    No Known Activations