© 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. 19-TRANSCODER-HP
    7. 8533
    Prev
    Next
    INDEX
    Explanations

    named after/because

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åijĬè¯ī大家
    -0.30
    ä»ĸ认为
    -0.29
     PROGMEM
    -0.27
    åijĬè¯īä»ĸ
    -0.27
    ä»ĸ表示
    -0.27
    .au
    -0.26
    ANCE
    -0.26
    older
    -0.26
     horrified
    -0.25
    åĨ³å®ļäºĨ
    -0.25
    POSITIVE LOGITS
    sg
    0.27
     subt
    0.26
    åįł
    0.25
    éĺ´
    0.25
    tat
    0.24
    issing
    0.23
     Mog
    0.23
     Lat
    0.23
     gep
    0.23
     situated
    0.23
    Activations Density 0.018%

    No Known Activations