© 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. 7921
    Prev
    Next
    INDEX
    Explanations

    the

    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
     luk
    -0.26
     individual
    -0.26
    mw
    -0.25
    æľĢåĪĿçļĦ
    -0.25
    éļı
    -0.24
    .proto
    -0.24
    wnd
    -0.24
    æľī人
    -0.24
    iciencies
    -0.24
    RunWith
    -0.24
    POSITIVE LOGITS
    ensburg
    0.29
    =length
    0.28
    åİ»çľĭçľĭ
    0.26
    ibli
    0.25
     theirs
    0.25
    .bc
    0.25
    çļĦåIJĮåѦ
    0.25
    æѤ类
    0.24
     belonged
    0.24
    æĬij
    0.24
    Activations Density 0.009%

    No Known Activations