© 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. 30-TRANSCODER-HP
    7. 97069
    Prev
    Next
    INDEX
    Explanations

    sacrifice, dedication, or loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ĵåĮº
    -0.28
    âľİ
    -0.28
    éĢł
    -0.28
    su
    -0.26
    shortcode
    -0.25
    æĦıåIJij
    -0.25
    éĢģè¾¾
    -0.25
    .Checked
    -0.25
    CUS
    -0.25
    çijķ
    -0.25
    POSITIVE LOGITS
     for
    0.44
    for
    0.34
    ÑģÑĤеÑĢ
    0.29
    -for
    0.28
     in
    0.28
     winning
    0.27
    _for
    0.27
     losing
    0.26
    çļĦ主è¦ģ
    0.26
     fighting
    0.26
    Activations Density 0.104%

    No Known Activations