© 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. 64789
    Prev
    Next
    INDEX
    Explanations

    to

    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
    abouts
    -0.29
    å¯Ħæīĺ
    -0.27
     cafeteria
    -0.26
    illian
    -0.26
     foe
    -0.26
     crest
    -0.24
    迹
    -0.24
    éļĪ
    -0.24
    ä¹ĥæĺ¯
    -0.24
    åĬ©åѦ
    -0.23
    POSITIVE LOGITS
    éķĽ
    0.29
    æij©
    0.28
    ä¼ĺ
    0.27
     Rat
    0.26
    á»ijt
    0.25
    |x
    0.25
     Ring
    0.25
    OfSize
    0.24
    éĹ®é¢ĺ
    0.24
    optic
    0.24
    Activations Density 24.483%

    No Known Activations