© 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. 131062
    Prev
    Next
    INDEX
    Explanations

    technical configurations

    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
     Ton
    -0.27
    Liv
    -0.27
    ouch
    -0.27
     бил
    -0.27
    .bc
    -0.26
    Ton
    -0.26
    ipi
    -0.25
    bow
    -0.25
     cá
    -0.25
     uncon
    -0.25
    POSITIVE LOGITS
    zioni
    0.28
    é¦ĸåıij
    0.27
    éĤ£éĩĮ
    0.26
    ogi
    0.26
     Guard
    0.26
    -hide
    0.24
    å¤ĩçĶ¨
    0.24
     rank
    0.24
    SENS
    0.24
    åİ¥
    0.24
    Activations Density 15.152%

    No Known Activations