© 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. 20-TRANSCODER-HP
    7. 140542
    Prev
    Next
    INDEX
    Explanations

    shake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    PIO
    -0.31
    媲
    -0.27
     visitor
    -0.26
    _named
    -0.26
    pper
    -0.26
     course
    -0.26
    µľ
    -0.24
    ãģ¾ãģ¨
    -0.24
    ä¸ĵåijĺ
    -0.24
    pects
    -0.24
    POSITIVE LOGITS
    ä¼ļéķ¿
    0.27
    .transforms
    0.25
    侥幸
    0.25
    -blind
    0.25
    magnitude
    0.25
    éĥ½ä¸įä¼ļ
    0.24
     wrists
    0.24
     magn
    0.24
    ä½İåİĭ
    0.24
    ä¸įåıĺ
    0.24
    Activations Density 4.931%

    No Known Activations