© 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. 106861
    Prev
    Next
    INDEX
    Explanations

    Blue

    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
     translates
    -0.26
    Ty
    -0.26
    ty
    -0.26
    ä¸ĢäºĮ
    -0.25
    s
    -0.24
    lea
    -0.24
     Boards
    -0.24
    leÅŁ
    -0.23
    åĨħéĥ¨
    -0.23
    iddle
    -0.23
    POSITIVE LOGITS
    ndon
    0.29
    mutable
    0.28
    çĵł
    0.28
    blo
    0.27
    åŁ
    0.27
     Overs
    0.27
    -mask
    0.26
    bins
    0.26
    ↵    ↵    ↵
    0.26
    å¹Į
    0.26
    Activations Density 0.649%

    No Known Activations