© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    rich/high

    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
    cade
    -0.27
     ÐŁÑĢе
    -0.25
    æłĭ
    -0.25
    :update
    -0.25
     Marketplace
    -0.24
    arium
    -0.24
    åı¯çĸij
    -0.23
     recieved
    -0.23
     corrid
    -0.23
     surprised
    -0.23
    POSITIVE LOGITS
    èIJ½åľ¨
    0.26
    ä¸Ģåı£æ°Ķ
    0.26
    ç«Ļåľ¨
    0.26
    iff
    0.25
     both
    0.24
     product
    0.24
    curve
    0.24
    mod
    0.24
    /sl
    0.23
     Greek
    0.23
    Activations Density 0.039%

    No Known Activations