© 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. 19-TRANSCODER-HP
    7. 6171
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    个ä½ĵ
    -0.25
    éĢļçĶ¨
    -0.24
    æľĽ
    -0.24
    æĬķèµĦ
    -0.24
    ounce
    -0.24
     dashes
    -0.23
     设
    -0.23
    ALLOC
    -0.23
    æĬµ
    -0.23
    ubic
    -0.23
    POSITIVE LOGITS
    è¸Į
    0.28
    _End
    0.27
    Nor
    0.26
    æĥ³åİ»
    0.25
     mur
    0.25
     killer
    0.24
    EndPoint
    0.24
     bình
    0.24
    locals
    0.24
    踩
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.