© 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. 8956
    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
    asan
    -0.28
    Technical
    -0.28
     Technical
    -0.25
    iej
    -0.24
    èµ·ä¼ı
    -0.24
    Neg
    -0.24
     unint
    -0.23
    urch
    -0.23
    #End
    -0.23
     til
    -0.23
    POSITIVE LOGITS
    åľ¨æĦı
    0.27
    arella
    0.27
     pymysql
    0.26
    extr
    0.25
     perfected
    0.25
    моÑĤÑĢ
    0.24
    cae
    0.23
    enk
    0.23
     routed
    0.23
    èĢĥèĻijåĪ°
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.