© 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. 7266
    Prev
    Next
    INDEX
    Explanations

    time

    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
    æĹ©æĹ¥
    -0.26
    rew
    -0.26
    è¿Ļä¸ĢçĤ¹
    -0.24
    tridge
    -0.24
    module
    -0.23
    èµ°åĩº
    -0.23
    prior
    -0.23
     steep
    -0.23
    uide
    -0.23
    tw
    -0.23
    POSITIVE LOGITS
    овал
    0.27
    adays
    0.27
    NP
    0.26
    ÑĨов
    0.26
    edException
    0.26
    edImage
    0.25
     Subway
    0.25
    çľģæĶ¿åºľ
    0.25
    (confirm
    0.24
     Bison
    0.24
    Activations Density 0.154%

    No Known Activations