© 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. 30334
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    andal
    -0.30
    ouri
    -0.26
    çļĦå¢ŀéķ¿
    -0.25
    ä¸ĢæĬĬ
    -0.24
    isposable
    -0.24
    holder
    -0.24
    -holder
    -0.24
    prises
    -0.24
     Attached
    -0.24
     earners
    -0.23
    POSITIVE LOGITS
    пед
    0.32
    éĽķ
    0.28
     Lod
    0.26
    iel
    0.24
     online
    0.24
     log
    0.24
    -online
    0.24
    -log
    0.24
    smith
    0.24
    Y
    0.23
    Activations Density 0.533%

    No Known Activations