© 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. 30-TRANSCODER-HP
    7. 96007
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useForm
    -0.26
    å¼±åĬ¿
    -0.26
    èŃ·
    -0.25
     {}).
    -0.25
    {return
    -0.25
    {name
    -0.25
    å½¢å¼ı
    -0.25
    (parsed
    -0.25
    CTYPE
    -0.24
    çļĦæľ¬è´¨
    -0.24
    POSITIVE LOGITS
    ocket
    0.27
    buch
    0.25
    rq
    0.25
    贯彻
    0.24
     Spicer
    0.24
    ÑĤвеÑĢд
    0.23
    yle
    0.23
    yclopedia
    0.23
    çļĦ妻åŃIJ
    0.23
    gL
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.