© 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. 129003
    Prev
    Next
    INDEX
    Explanations

    Descriptions of people/stories

    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
    etur
    -0.27
    åIJįé¢Ŀ
    -0.26
    éķ¿éķ¿çļĦ
    -0.26
     zad
    -0.25
    np
    -0.25
    ãģ»ãģ©
    -0.24
    æľĪåĪĿ
    -0.24
     Pil
    -0.23
     Assign
    -0.23
    +"\
    -0.23
    POSITIVE LOGITS
    dings
    0.31
     Dame
    0.29
    opard
    0.27
     unrelated
    0.27
    dia
    0.27
     sliced
    0.26
    stinence
    0.25
     Nicholas
    0.25
    tube
    0.25
     Sanford
    0.25
    Activations Density 11.158%

    No Known Activations