© 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. 141546
    Prev
    Next
    INDEX
    Explanations

    Verb "to be"

    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
    coop
    -0.28
    æĺ¯ä»ĸ
    -0.27
     Anyway
    -0.27
    ä¹Łæĺ¯å¾Ī
    -0.26
    brook
    -0.26
    bench
    -0.26
    baum
    -0.25
    pine
    -0.25
    ç®ĹäºĨ
    -0.25
    èĴľ
    -0.25
    POSITIVE LOGITS
    èĩ³
    0.26
    åħ¶ä¸Ń
    0.26
    ubit
    0.26
    ç¿Ģ
    0.25
    ế
    0.25
    dict
    0.25
    amp
    0.24
    éĻħ
    0.24
     ont
    0.24
     An
    0.24
    Activations Density 45.831%

    No Known Activations