© 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. 63897
    Prev
    Next
    INDEX
    Explanations

    term

    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
    atical
    -0.29
    alo
    -0.26
    ä¸įåĨįæĺ¯
    -0.25
    IED
    -0.25
    èĢķèĢĺ
    -0.24
    ä¸įå°½
    -0.23
     wandering
    -0.23
     Reign
    -0.23
    antom
    -0.23
    ä¸įåĨį
    -0.23
    POSITIVE LOGITS
    çī¹æľĹ
    0.28
    urat
    0.28
    abar
    0.26
    orris
    0.26
     PageInfo
    0.24
     cust
    0.24
    让大家
    0.23
    âĦ¹
    0.23
    -ul
    0.23
    plat
    0.23
    Activations Density 3.653%

    No Known Activations