© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8520
    Prev
    Next
    INDEX
    Explanations

    interesting

    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
    éĿ
    -0.27
    oux
    -0.26
    ody
    -0.26
     independently
    -0.25
    主ä½ĵ
    -0.25
    achment
    -0.24
    é¡
    -0.24
    quit
    -0.24
     independence
    -0.24
     substance
    -0.23
    POSITIVE LOGITS
    éªĹåıĸ
    0.30
    æĹ¥æ¶Īæģ¯
    0.26
    æĿĨèıĮ
    0.26
    stadt
    0.25
    TURE
    0.25
     mù
    0.25
    年人
    0.24
    ORIZED
    0.24
    ä¸Ģéģĵ
    0.24
    blockquote
    0.23
    Activations Density 0.026%

    No Known Activations