© 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. 25-TRANSCODER-HP
    7. 109506
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dig
    -0.31
     dig
    -0.26
     hers
    -0.25
    èĸ°
    -0.24
     />\
    -0.24
     setInput
    -0.24
     proph
    -0.24
    лог
    -0.24
    oler
    -0.24
    ä¸Ģé¦ĸ
    -0.23
    POSITIVE LOGITS
    Web
    0.31
     web
    0.28
     Web
    0.27
    -LAST
    0.24
     mạng
    0.24
    $")↵
    0.24
    inet
    0.24
    /Web
    0.23
    身价
    0.23
    osa
    0.23
    Activations Density 0.895%

    No Known Activations