© 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. 6249
    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
    itori
    -0.28
    ="<<
    -0.27
    æĺ¯æĮĩ
    -0.27
    第ä¸Ģä½į
    -0.26
    è¿ĻäºĽä¸ľè¥¿
    -0.25
    лав
    -0.24
    罩
    -0.24
    LookAndFeel
    -0.24
     Mk
    -0.24
    åķĨä¼ļ
    -0.24
    POSITIVE LOGITS
    apas
    0.27
     Cup
    0.26
     clip
    0.25
    atively
    0.25
    amu
    0.25
    führung
    0.24
     precis
    0.24
     sip
    0.24
    lig
    0.24
     Roh
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.