© 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. 6640
    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
    鬼
    -0.26
    åijĬ
    -0.26
    ç«ŀäºīåĬĽ
    -0.25
    ogh
    -0.24
    åļı
    -0.24
    etadata
    -0.24
     ghost
    -0.24
    å²ģ以ä¸ĭ
    -0.24
    èĬĤ
    -0.24
     strang
    -0.24
    POSITIVE LOGITS
    umas
    0.25
     fu
    0.23
     Diss
    0.23
    ugo
    0.23
    pheric
    0.23
    armed
    0.23
     ones
    0.23
     Dustin
    0.22
     analogy
    0.22
     Slovak
    0.22
    Activations Density 0.243%

    No Known Activations

    This feature has no known activations.