© 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. 4964
    Prev
    Next
    INDEX
    Explanations

    Oil

    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
    Contained
    -0.25
    å¾Īæ¸ħæ¥ļ
    -0.24
    calar
    -0.23
    ä¸įçIJĨ
    -0.23
    ä»»ä½ķ人éĥ½
    -0.22
    åĴĮåľ°åĮº
    -0.22
    ä¹³æĪ¿
    -0.22
    redi
    -0.22
    ä¸ĢåĽ¢
    -0.22
     Worldwide
    -0.22
    POSITIVE LOGITS
     runoff
    0.28
    ees
    0.28
    ä¸Ģæł·çļĦ
    0.27
     summ
    0.25
    /photo
    0.24
    ward
    0.23
    çļĦå¿ĥçIJĨ
    0.23
    /lab
    0.23
    åĨ¶éĩij
    0.23
    ness
    0.22
    Activations Density 0.658%

    No Known Activations