© 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. 6072
    Prev
    Next
    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    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
    å¼ıçļĦ
    -0.28
    è¾ĩ
    -0.28
    arin
    -0.27
    åijĬè¯ī她
    -0.27
    级åĪ«çļĦ
    -0.27
    .addObserver
    -0.25
    ä¹ĭä¸Ģ
    -0.25
    ARC
    -0.25
     fails
    -0.25
    (fn
    -0.24
    POSITIVE LOGITS
    |--
    0.28
    åij½
    0.26
    inspace
    0.25
     entert
    0.25
    alem
    0.24
    çī¯
    0.24
    orges
    0.24
    <head
    0.24
     Alternate
    0.24
    Alternate
    0.24
    Activations Density 0.019%

    No Known Activations