© 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. 5998
    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
    stein
    -0.32
    oved
    -0.30
     Laden
    -0.27
    culate
    -0.26
    åĽ¾ä¸º
    -0.26
    leg
    -0.24
    ProcessEvent
    -0.24
    _loaded
    -0.24
    奶èĮ¶
    -0.24
    quil
    -0.24
    POSITIVE LOGITS
    cors
    0.27
    è¶Ĭ好
    0.25
    ÙħزÙĬد
    0.25
    wie
    0.24
     Fold
    0.24
    $value
    0.24
    SURE
    0.24
    uka
    0.23
    UAL
    0.23
    æĬĺ
    0.23
    Activations Density 0.040%

    No Known Activations

    This feature has no known activations.