© 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. 64726
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    INO
    -0.29
    ino
    -0.26
    resh
    -0.25
    än
    -0.25
    å½ĵä½ł
    -0.24
     Pager
    -0.24
    åĽ½å®¶
    -0.24
    们çļĦ
    -0.24
    æľĢåĪĿçļĦ
    -0.23
    æ½ĺ
    -0.23
    POSITIVE LOGITS
    款
    0.27
    ä¸Ģäºĭ
    0.26
    座
    0.26
    ington
    0.25
     measurable
    0.24
     occ
    0.24
     Wich
    0.24
     meme
    0.23
    askell
    0.23
    æŀķ
    0.23
    Activations Density 2.837%

    No Known Activations