© 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. 7428
    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
     каз
    -0.25
     ÐŁÐµÑĤ
    -0.24
     shaken
    -0.23
    å¤ĦçIJĨ
    -0.23
     gev
    -0.23
     пеÑĢе
    -0.23
    åijĬè¯īæĪij们
    -0.23
    踩
    -0.23
    ften
    -0.23
    è¿Ļæł·ä¸Ģ个
    -0.23
    POSITIVE LOGITS
    -square
    0.27
     Square
    0.26
    bows
    0.26
    Äĥn
    0.25
    åĪĹ
    0.25
    ps
    0.25
    _square
    0.25
    çıį
    0.25
    èµĸ以çĶŁåŃĺ
    0.24
    åĺ¹
    0.24
    Activations Density 0.288%

    No Known Activations

    This feature has no known activations.