© 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. 98178
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ANA
    -0.29
    EB
    -0.28
    AMS
    -0.27
    ENE
    -0.26
    eds
    -0.25
    wards
    -0.25
    Bottom
    -0.24
    (ct
    -0.24
     Futures
    -0.24
     Gro
    -0.23
    POSITIVE LOGITS
    reste
    0.27
    æĢ§å¼º
    0.27
    æ°Ķè´¨
    0.26
    ä¹Ĺ
    0.26
    .Sdk
    0.25
    ç½ijç«Ļé¦ĸ页
    0.25
    cona
    0.24
    çļĦ女人
    0.23
    éĴ¢æĿ¿
    0.23
    åıijçİ°éĹ®é¢ĺ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.