© 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. 27-TRANSCODER-HP
    7. 57053
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¼èģĮ
    -0.28
    å¥
    -0.26
    enberg
    -0.25
    åĩłå¼ł
    -0.25
    agraph
    -0.25
    atro
    -0.24
    伯
    -0.24
    etri
    -0.24
    è¾¾å°Ķ
    -0.24
    portlet
    -0.23
    POSITIVE LOGITS
     geçmiÅŁ
    0.27
    绿水
    0.26
    //}↵↵
    0.25
    Õ±
    0.24
    åıijåŀĭ
    0.24
     measuring
    0.24
    å²©çŁ³
    0.24
     FuÃŁ
    0.24
    miÅŁ
    0.24
    gress
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.