© 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. 108574
    Prev
    Next
    INDEX
    Explanations

    Code, errors, technical 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
    缴åĪ°
    -0.58
    æļĤæŶ
    -0.57
     temporarily
    -0.55
     until
    -0.53
     initially
    -0.52
    åĪĿæľŁ
    -0.51
    缴èĩ³
    -0.48
     initial
    -0.48
     temporary
    -0.48
    çŁŃæľŁåĨħ
    -0.47
    POSITIVE LOGITS
    Avg
    0.28
    羣çĪ±
    0.27
    ä¸įç®¡ä½ł
    0.27
    -commercial
    0.26
     artık
    0.26
    ள
    0.26
    说èĩªå·±
    0.25
    Ĩµ
    0.25
     Chan
    0.25
    éĤ£åıª
    0.24
    Activations Density 44.339%

    No Known Activations