© 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. 22306
    Prev
    Next
    INDEX
    Explanations

    shapes and coding snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.27
    ãģ¨ãģĨ
    -0.27
    orical
    -0.26
    ìĬ¤íĬ¸
    -0.25
    rott
    -0.24
    OMETRY
    -0.24
    Concept
    -0.24
     Concept
    -0.24
    ðĿľĭ
    -0.24
     concept
    -0.23
    POSITIVE LOGITS
     bend
    0.31
    身
    0.28
    item
    0.27
    -FIRST
    0.25
    æĿ¯
    0.25
    åıĹ
    0.25
    å¸Ŀçİĭ
    0.25
    æĻļ
    0.25
    åIJĽ
    0.24
    å°ıä¼Ļ
    0.24
    Activations Density 0.000%

    No Known Activations