© 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. 20-TRANSCODER-HP
    7. 129816
    Prev
    Next
    INDEX
    Explanations

    enhance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pliers
    -0.24
    elight
    -0.24
    aires
    -0.24
    alue
    -0.23
     act
    -0.23
    éªļ
    -0.23
    .logic
    -0.23
    çīĮ
    -0.23
     Army
    -0.23
    ictures
    -0.23
    POSITIVE LOGITS
    éĩį
    0.29
    大家åĪĨ享
    0.27
    /de
    0.27
    eea
    0.25
    æŸ
    0.25
    prit
    0.24
     panorama
    0.24
    æĪ¾
    0.23
    头æĿ¡
    0.23
    ɤ
    0.23
    Activations Density 15.273%

    No Known Activations