© 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. 30482
    Prev
    Next
    INDEX
    Explanations

    data structures

    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
    SSIP
    -0.30
     egret
    -0.28
    ellas
    -0.25
    anio
    -0.24
    ë¥ĺ
    -0.24
    -focused
    -0.24
    æ¹į
    -0.24
     Principal
    -0.23
    CUS
    -0.23
    èĭĴ
    -0.23
    POSITIVE LOGITS
    lement
    0.28
     complimentary
    0.27
     posi
    0.24
    çĽĶ
    0.24
     cover
    0.24
    è¦ĨçĽĸçİĩ
    0.24
    篷
    0.23
     structure
    0.23
    ???
    0.23
    ä»Ģä¹Īæł·çļĦ
    0.23
    Activations Density 0.681%

    No Known Activations