© 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. 142696
    Prev
    Next
    INDEX
    Explanations

    general english text

    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
    rie
    -0.26
     Grave
    -0.24
    concert
    -0.24
    ALT
    -0.24
     agre
    -0.24
    opt
    -0.24
    为æĤ¨
    -0.24
    ",{
    -0.24
    å¤Ķ
    -0.23
     openness
    -0.23
    POSITIVE LOGITS
    害ç¾ŀ
    0.32
    åIJĪåĩ»
    0.26
    ой
    0.26
    åıijåŀĭ
    0.25
    LayoutParams
    0.25
    TM
    0.25
     imagin
    0.25
    åĪĿä¸ī
    0.25
    ster
    0.25
    åĪĨåħ¬åı¸
    0.25
    Activations Density 14.860%

    No Known Activations