© 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. 9561
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    以人为
    -0.29
    cuts
    -0.27
     Hub
    -0.25
    åĢĮ
    -0.25
    人为
    -0.25
    å¹²èĦĨ
    -0.24
    _hex
    -0.24
    ulla
    -0.24
    åŃĺåľ¨ä¸Ģå®ļ
    -0.24
     Shell
    -0.24
    POSITIVE LOGITS
    çĻ¾ä¸ĩ
    0.41
     millions
    0.40
     thousands
    0.38
     million
    0.38
     Thousands
    0.37
     thousand
    0.37
    åįĥä¸ĩ
    0.37
    ä¸Ĭåįĥ
    0.35
    Thousands
    0.35
    åįģä¸ĩ
    0.35
    Activations Density 0.138%

    No Known Activations