© 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. 32-TRANSCODER-HP
    7. 40912
    Prev
    Next
    INDEX
    Explanations

    Countries ending in "stan"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĨĴäºĨ
    -0.31
    éĨĴ
    -0.28
    éĤ½
    -0.27
     inventory
    -0.26
    kid
    -0.26
    fans
    -0.25
    Īĺ
    -0.25
    éĨĴæĿ¥
    -0.24
    -ok
    -0.24
    matic
    -0.24
    POSITIVE LOGITS
    ab
    0.35
    aba
    0.33
    GridColumn
    0.30
     bent
    0.29
    NG
    0.28
     ab
    0.28
    Stand
    0.27
    овоÑĢ
    0.27
     sw
    0.27
     aba
    0.27
    Activations Density 0.001%

    No Known Activations