© 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. 20-TRANSCODER-HP
    7. 142759
    Prev
    Next
    INDEX
    Explanations

    political or economic conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħ¨æĹ¥åĪ¶
    -0.28
    ->__
    -0.28
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.27
    urg
    -0.26
    [__
    -0.26
    á»Ĩ
    -0.26
    çĽ¸äº²
    -0.25
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.25
    iline
    -0.25
    abor
    -0.25
    POSITIVE LOGITS
     DBNull
    0.25
    ipple
    0.25
    åŀĦ
    0.25
    ">${
    0.24
    erp
    0.24
     gilt
    0.24
    rices
    0.24
     lig
    0.23
     Cisco
    0.23
    åıĹ
    0.23
    Activations Density 12.187%

    No Known Activations