© 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. 22-TRANSCODER-HP
    7. 98845
    Prev
    Next
    INDEX
    Explanations

    Specialized terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensively
    -0.26
    è¿Ļæĸ¹éĿ¢
    -0.25
    ãģĵãĤĮ
    -0.24
    lier
    -0.24
    atial
    -0.24
    ünst
    -0.24
    è¶Ĭæĺ¯
    -0.23
    åŀĤ缴
    -0.23
     '&'
    -0.22
    /tcp
    -0.22
    POSITIVE LOGITS
     overtime
    0.26
    Shar
    0.25
     rounds
    0.25
    /documentation
    0.25
    Filed
    0.25
    æīĢ产çĶŁçļĦ
    0.25
     accounting
    0.24
    身价
    0.24
    rary
    0.24
    ottes
    0.24
    Activations Density 0.012%

    No Known Activations