© 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. 32-TRANSCODER-HP
    7. 40810
    Prev
    Next
    INDEX
    Explanations

    vocabulary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¯Ńè¨Ģ
    -0.32
     lang
    -0.31
    èªŀè¨Ģ
    -0.30
    language
    -0.30
     Lang
    -0.30
    lang
    -0.28
     language
    -0.28
    Lang
    -0.27
    )init
    -0.27
    婳
    -0.26
    POSITIVE LOGITS
     acquired
    0.32
     Build
    0.30
    Build
    0.30
     gained
    0.29
     build
    0.29
     builder
    0.29
    建åįİ
    0.28
    enko
    0.28
     BUILD
    0.28
    Builder
    0.27
    Activations Density 0.001%

    No Known Activations