© 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. 6622
    Prev
    Next
    INDEX
    Explanations

    $

    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
    emente
    -0.27
     healthier
    -0.26
    endor
    -0.26
    éĺ»
    -0.26
    (inertia
    -0.26
    hind
    -0.25
    æŃ£åĵģ
    -0.25
    &action
    -0.24
    IVA
    -0.24
    &e
    -0.24
    POSITIVE LOGITS
    oppers
    0.27
    个
    0.27
    æĪijä»¬åľ¨
    0.25
    tre
    0.24
    opping
    0.24
    æĢ»çļĦ
    0.24
    éĤ£ä¹Īå¤ļ
    0.24
     aantal
    0.24
     amount
    0.23
    åħijçİ°
    0.23
    Activations Density 0.203%

    No Known Activations