© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129038
    Prev
    Next
    INDEX
    Explanations

    Code, not, nothing

    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
    Negative Logits
    tron
    -0.27
    hort
    -0.27
    ason
    -0.26
    ased
    -0.26
    èĢĮä¸įæĺ¯
    -0.26
     SOUR
    -0.26
    estar
    -0.25
    ôi
    -0.24
     instead
    -0.24
    itters
    -0.24
    POSITIVE LOGITS
    WARE
    0.25
    éĢģåĪ°
    0.24
     logging
    0.24
    обÑĢажен
    0.24
    éĢģåİ»
    0.24
     HOL
    0.24
     Wich
    0.24
    çħ
    0.23
    åģľäº§
    0.23
    typename
    0.23
    Activations Density 6.443%

    No Known Activations