© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7267
    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
    çīµ
    -0.29
    ungen
    -0.25
    éĻIJ
    -0.24
    иÑĩ
    -0.23
    Denied
    -0.23
    åŁİ
    -0.23
    дал
    -0.23
    å½³
    -0.23
    ä¸į足以
    -0.23
    ATO
    -0.22
    POSITIVE LOGITS
    åĩłåı¥
    0.27
     volunt
    0.26
     harness
    0.25
    åŀ®
    0.25
     nood
    0.25
    è¿Ļæł·ä¸Ģ
    0.25
    woke
    0.25
     emerge
    0.24
    atives
    0.24
     cuent
    0.24
    Activations Density 0.051%

    No Known Activations

    This feature has no known activations.