© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163035
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eton
    -0.27
     circuits
    -0.26
    é¦ĸæī¹
    -0.24
    ãĤĪãģĨãģ§
    -0.24
    èħ®
    -0.24
    æı©
    -0.24
    ibble
    -0.24
    herit
    -0.23
    天çĦ¶
    -0.23
    éĢ»è¾ij
    -0.23
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.26
     ÑĥÑģл
    0.26
    PJ
    0.25
    æģIJ
    0.24
    ARGV
    0.24
    xDE
    0.23
     convolution
    0.23
    ymb
    0.23
     har
    0.23
    gars
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.