© 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. 30458
    Prev
    Next
    INDEX
    Explanations

    imp

    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
    Clone
    -0.28
    ç»Ŀ
    -0.26
    inning
    -0.26
    æĮĩæľĽ
    -0.26
     aer
    -0.26
     enchanted
    -0.25
    ect
    -0.25
    roph
    -0.25
    é¢ĦæľŁ
    -0.25
     crossing
    -0.25
    POSITIVE LOGITS
    )').
    0.27
    utive
    0.26
    ä¹°
    0.26
    庸
    0.25
    xBE
    0.25
    backs
    0.25
    IALIZED
    0.24
    èij¬
    0.24
    ä¹°çļĦ
    0.24
    osas
    0.23
    Activations Density 0.240%

    No Known Activations