© 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. 140550
    Prev
    Next
    INDEX
    Explanations

    Numbers, plans, code

    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
     old
    -0.33
    Original
    -0.32
    æŧ
    -0.32
    èĪĬ
    -0.32
    Old
    -0.31
     original
    -0.31
     Original
    -0.31
    åİŁæĿ¥çļĦ
    -0.29
    Own
    -0.29
     Old
    -0.29
    POSITIVE LOGITS
    çݰ代çī©æµģ
    0.31
    第äºĮèĬĤ
    0.29
    etas
    0.28
    èĪįå¾Ĺ
    0.27
     newRow
    0.27
    第ä¸ĢèĬĤ
    0.27
     resourceName
    0.27
    æĪ´ä¸Ĭ
    0.26
    [mask
    0.25
    )new
    0.25
    Activations Density 8.716%

    No Known Activations