© 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. 107450
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    ächt
    -0.31
    errer
    -0.27
    ENTE
    -0.27
     sắc
    -0.26
    ente
    -0.26
    vir
    -0.25
     nữa
    -0.25
    绪
    -0.24
    аÑĤÑĮÑģÑı
    -0.24
    NODE
    -0.23
    POSITIVE LOGITS
    çĤ¹åįĬ
    0.26
    åIJ»
    0.26
    åħ¸åŀĭçļĦ
    0.25
     cancell
    0.25
    çļĦåĽŀçŃĶ
    0.25
    -INF
    0.24
    ä¼łåĩº
    0.23
     OMIT
    0.23
    _ABC
    0.23
    _tunnel
    0.23
    Activations Density 29.196%

    No Known Activations