© 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. 62815
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    itty
    -0.29
    æīĵä»Ĺ
    -0.26
    urs
    -0.25
    èħ°éĥ¨
    -0.24
    Emb
    -0.24
    ders
    -0.23
    tracts
    -0.23
    ientes
    -0.23
    VN
    -0.23
     yet
    -0.23
    POSITIVE LOGITS
    edy
    0.26
    apy
    0.25
    深深
    0.25
    aping
    0.24
    æĺ¯ä¸Ģ家
    0.24
    ä¸Ģè¡Į
    0.23
    網
    0.23
    ä»ħ次äºİ
    0.23
    æ¼Ķ
    0.23
     ([]
    0.22
    Activations Density 2.010%

    No Known Activations