© 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. 18-TRANSCODER-HP
    7. 89632
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĶģå®ļ
    -0.28
    rote
    -0.28
    [Y
    -0.27
    aldi
    -0.26
    æ¸ħæī«
    -0.25
     sinks
    -0.24
    æĹłè§Ĩ
    -0.24
    ubber
    -0.24
    .Ge
    -0.24
     mức
    -0.23
    POSITIVE LOGITS
    Ensure
    0.27
    -slot
    0.27
    berger
    0.26
    losion
    0.25
     Ensure
    0.25
    arial
    0.24
    æľĢ好çļĦ
    0.24
    çļĦèĥ½åĬĽ
    0.24
     best
    0.24
     tallest
    0.24
    Activations Density 0.128%

    No Known Activations

    This feature has no known activations.