© 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. 24-TRANSCODER-HP
    7. 150059
    Prev
    Next
    INDEX
    Explanations

    code/unusual writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bring
    -0.27
    篷
    -0.25
     sights
    -0.24
    æīĭæĮĩ
    -0.24
    满æĦı
    -0.24
     wrought
    -0.24
     brought
    -0.23
     fil
    -0.23
    izard
    -0.23
    >>>
    -0.23
    POSITIVE LOGITS
     thuyết
    0.27
    ution
    0.26
    ocode
    0.26
     ÐłÐµ
    0.26
    èİ«æĸ¯
    0.26
    çħ§
    0.25
    æĿ¥æºIJ
    0.25
     cả
    0.24
    åŁ¤
    0.24
    代çłģ
    0.24
    Activations Density 0.106%

    No Known Activations