© 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. 14-TRANSCODER-HP
    7. 40841
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľªæĪIJ年人
    -0.27
    åħħå®ŀ
    -0.25
    ä¸įæĪIJ
    -0.25
    ãĤ¢ãĥĬ
    -0.24
     ut
    -0.24
    PageRoute
    -0.24
     phase
    -0.24
    æľªæĪIJå¹´
    -0.24
    çļĦåĬ¨åĬĽ
    -0.23
     Initialize
    -0.23
    POSITIVE LOGITS
     bottoms
    0.28
    obia
    0.28
    anked
    0.27
    åľ¨çº¿
    0.27
    \db
    0.27
    unning
    0.27
     coma
    0.26
    /cpu
    0.26
    [op
    0.25
     PROP
    0.24
    Activations Density 0.534%

    No Known Activations

    This feature has no known activations.