© 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. 129141
    Prev
    Next
    INDEX
    Explanations

    government

    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
    ayne
    -0.28
    erals
    -0.27
     Goth
    -0.26
    owler
    -0.25
    åħ±åIJĮåıijå±ķ
    -0.25
    ))+
    -0.25
    KNOWN
    -0.24
    burgh
    -0.24
     immedi
    -0.24
    frage
    -0.24
    POSITIVE LOGITS
    积水
    0.29
    .fil
    0.28
    äºĨä¸ĢäºĽ
    0.27
    çļĦåĬŀæ³ķ
    0.26
    anas
    0.26
    à¤Ľ
    0.26
    æĭĴ
    0.25
    ç°ĩ
    0.25
    æĪŁ
    0.25
    adge
    0.25
    Activations Density 4.221%

    No Known Activations