© 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. 62683
    Prev
    Next
    INDEX
    Explanations

    fragmented information

    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
    çĤ¹
    -0.30
    rm
    -0.28
    æĮģ
    -0.25
    ASF
    -0.25
     D
    -0.25
    Vis
    -0.25
    wei
    -0.24
     Young
    -0.24
    asti
    -0.24
     point
    -0.24
    POSITIVE LOGITS
     IMPLEMENT
    0.26
    OnInit
    0.25
    TestClass
    0.24
    âĺ¯
    0.24
    -Javadoc
    0.24
    èĩĮ
    0.24
    管çIJĨ模å¼ı
    0.24
    åİŁæľīçļĦ
    0.23
    _^
    0.23
     Caj
    0.23
    Activations Density 2.994%

    No Known Activations