© 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. 24-TRANSCODER-HP
    7. 149371
    Prev
    Next
    INDEX
    Explanations

    world trade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     population
    -0.30
    iesz
    -0.26
     populations
    -0.26
    人群ä¸Ń
    -0.26
    ABCDEFGHIJKLMNOP
    -0.25
    cies
    -0.25
    oise
    -0.25
    ademic
    -0.25
    è¡Įä¸ļä¸Ń
    -0.24
    人群
    -0.24
    POSITIVE LOGITS
     naw
    0.31
     меÑĢ
    0.29
     getState
    0.24
    liner
    0.24
    ä¹ĭå¤ľ
    0.23
     davon
    0.23
     Newman
    0.23
    ä¸Ńå°ıåŀĭ
    0.23
    -New
    0.23
    foods
    0.23
    Activations Density 0.219%

    No Known Activations