© 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. 19-TRANSCODER-HP
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    diary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ullet
    -0.29
    èĭ±çī¹
    -0.28
    CancelButton
    -0.25
    inja
    -0.25
    åĩĩ
    -0.24
    CGSize
    -0.24
    éķ¿çĽ¸
    -0.24
    ancode
    -0.23
    rtl
    -0.23
    аниÑİ
    -0.23
    POSITIVE LOGITS
    åij¨
    0.31
    çľĭ
    0.28
    èĢĮ
    0.27
    sumer
    0.27
     whereas
    0.26
    енко
    0.25
    页
    0.25
     pitch
    0.24
    æ±Ĺ
    0.24
    è£ı
    0.24
    Activations Density 0.145%

    No Known Activations