© 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. 6124
    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
    æĹłä¸į
    -0.28
    å¤ļå¹´çļĦ
    -0.25
    æłĩ
    -0.25
     Gross
    -0.25
     Ground
    -0.25
    åĩłçĤ¹
    -0.25
    оÑĤов
    -0.24
    osal
    -0.24
    ä½ķåĨµ
    -0.24
    å¼Ģ车
    -0.23
    POSITIVE LOGITS
    oline
    0.28
    ess
    0.26
    ict
    0.26
     borr
    0.26
    uned
    0.25
    æĪijçľģ
    0.25
    alto
    0.25
    ients
    0.25
    osity
    0.25
    ened
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.