© 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. 25345
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Enlightenment
    -0.25
     globalization
    -0.24
     laws
    -0.24
    è¨Ĺ
    -0.24
     rules
    -0.24
     ruler
    -0.24
     Magnus
    -0.23
    -transparent
    -0.23
    .communic
    -0.23
     throne
    -0.23
    POSITIVE LOGITS
    åĿļ硬
    0.28
    åĪ·æĸ°
    0.26
    ä¸Ģåı¥è¯Ŀ
    0.26
    urn
    0.26
    ÑĥÑģ
    0.26
     Saras
    0.25
    inflate
    0.25
    alez
    0.25
    zsche
    0.25
    .inflate
    0.25
    Activations Density 0.001%

    No Known Activations