© 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. 9-TRANSCODER-HP
    7. 29205
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¼´
    -0.26
     Licensed
    -0.26
     key
    -0.26
    è¿ĺæĺ¯
    -0.26
    害
    -0.26
    è¾ĵç»Ļ
    -0.26
     hardware
    -0.25
    newInstance
    -0.25
    åĨķ
    -0.25
    -
    -0.25
    POSITIVE LOGITS
    PTY
    0.27
    elong
    0.26
    emens
    0.25
    washer
    0.25
     groupId
    0.25
    reck
    0.25
     hơi
    0.25
     pymysql
    0.24
    artisan
    0.24
    ipline
    0.24
    Activations Density 1.109%

    No Known Activations