© 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. 129253
    Prev
    Next
    INDEX
    Explanations

    and,

    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
     douche
    -0.26
     SE
    -0.25
     potentially
    -0.25
     Logical
    -0.25
    .qual
    -0.25
     lad
    -0.24
    legg
    -0.24
    SEM
    -0.23
     unwind
    -0.23
    èĥ½å¾ĹåĪ°
    -0.23
    POSITIVE LOGITS
    aines
    0.28
    æŃ£æĸĩ
    0.25
    ä¸ĢæľŁ
    0.25
    é¦ĸåıij
    0.24
    atories
    0.24
     blocker
    0.24
    nown
    0.23
    ç¥ŀç»ıç³»ç»Ł
    0.23
    decl
    0.23
    å·²äºİ
    0.23
    Activations Density 10.685%

    No Known Activations