© 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. 108402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     substituted
    -0.30
     pretended
    -0.24
     tertiary
    -0.24
     everything
    -0.24
    egot
    -0.24
    æ±Ŀ
    -0.23
     tapi
    -0.23
     ETA
    -0.23
    entai
    -0.23
    onth
    -0.23
    POSITIVE LOGITS
    ahoo
    0.28
    éĴĪ
    0.26
    æķijæĬ¤
    0.25
    åĸĩåıŃ
    0.25
    çĶļ
    0.25
    wake
    0.25
    клад
    0.24
    веден
    0.24
    æĿı
    0.24
    æł·çļĦ
    0.24
    Activations Density 1.472%

    No Known Activations

    This feature has no known activations.