© 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. 27-TRANSCODER-HP
    7. 9650
    Prev
    Next
    INDEX
    Explanations

    Lists of technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -0.40
    ,and
    -0.38
    åĴĮ社ä¼ļ
    -0.37
     And
    -0.35
     vÃł
    -0.34
     à¹ģละ
    -0.33
    andin
    -0.33
    And
    -0.32
     AND
    -0.32
    åĴĮæĬĢæľ¯
    -0.32
    POSITIVE LOGITS
    ãĢģ
    0.46
    ãĢģ“
    0.31
    ãĢģãĢĮ
    0.30
    ãĢģãĢģ
    0.29
    ､
    0.26
     âĶľâĶĢâĶĢ
    0.26
    ï¼īãĢģ
    0.25
    und
    0.25
    ilm
    0.24
    éĢ¢
    0.24
    Activations Density 0.001%

    No Known Activations