© 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. 64881
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    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
    表æī¬
    -0.35
    å¥ĸåĬ±
    -0.33
    æĮĩ令
    -0.33
    è³ŀ
    -0.30
    å¥ĸ
    -0.29
    åħģ许
    -0.29
     reward
    -0.29
    reward
    -0.28
     Reward
    -0.27
    æĥ©ç½ļ
    -0.27
    POSITIVE LOGITS
     brun
    0.28
    ubre
    0.26
    mit
    0.26
    afa
    0.26
    ongs
    0.25
    atinum
    0.25
    trip
    0.24
    held
    0.24
     onSubmit
    0.24
    -sales
    0.24
    Activations Density 33.728%

    No Known Activations