© 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. 5049
    Prev
    Next
    INDEX
    Explanations

    Conversational context

    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
     technically
    -0.34
    ä»ħä»ħæĺ¯
    -0.29
    æĪĴ
    -0.28
    åıªæĺ¯ä¸Ģ个
    -0.28
    angered
    -0.28
     dece
    -0.26
    表éĿ¢
    -0.26
     bic
    -0.26
     technical
    -0.26
    çļĦæĬĢæľ¯
    -0.25
    POSITIVE LOGITS
    ecute
    0.28
    Validity
    0.28
     mel
    0.26
    许
    0.26
    interaction
    0.26
    丫
    0.26
     hold
    0.26
     Carol
    0.25
    ?url
    0.25
    æĹłå½¢
    0.24
    Activations Density 0.010%

    No Known Activations