© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53721
    Prev
    Next
    INDEX
    Explanations

    brands and companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IJľ
    -0.28
    éĢī
    -0.25
     sil
    -0.25
    å¾Ĵ
    -0.25
    &lt
    -0.24
    enan
    -0.24
    infinity
    -0.24
    æľīèĥ½åĬĽ
    -0.24
    oku
    -0.24
    ë°ľ
    -0.24
    POSITIVE LOGITS
    Serve
    0.26
     Nested
    0.26
    layui
    0.26
     Serg
    0.26
     Branch
    0.25
    CSI
    0.25
     Sawyer
    0.25
    мед
    0.24
    éĶ¥
    0.24
     pinned
    0.24
    Activations Density 0.015%

    No Known Activations